{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/ntk/papers/2","list_of":"/method/ntk","method":"NTK","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":233,"counts":{"archive_papers_tagged":233,"with_a_code_link":72,"where_syntology_ran_a_sample":35,"not_listed_spam_title":0,"listed":233,"listed_where_code_ran":35,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":26,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":26,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/ntk","prev":"/method/ntk","next":"/method/ntk/papers/3","papers":[{"paper":null,"slug":"efficient-ntk-using-dimensionality-reduction","title":"Efficient NTK using Dimensionality Reduction","date":"2022-10-10","arxiv_id":"2210.04807","n_code_links":0,"syntology":null},{"paper":null,"slug":"second-order-regression-models-exhibit","title":"Second-order regression models exhibit progressive sharpening to the edge of stability","date":"2022-10-10","arxiv_id":"2210.04860","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-influence-of-learning-rule-on","title":"The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks","date":"2022-10-05","arxiv_id":"2210.02157","n_code_links":0,"syntology":null},{"paper":null,"slug":"extrapolation-and-spectral-bias-of-neural","title":"Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study","date":"2022-09-16","arxiv_id":"2209.07736","n_code_links":0,"syntology":null},{"paper":"/paper/generalization-properties-of-nas-under","slug":"generalization-properties-of-nas-under","title":"Generalization Properties of NAS under Activation and Skip Connection Search","date":"2022-09-15","arxiv_id":"2209.07238","n_code_links":0,"syntology":null},{"paper":"/paper/fast-neural-kernel-embeddings-for-general","slug":"fast-neural-kernel-embeddings-for-general","title":"Fast Neural Kernel Embeddings for General Activations","date":"2022-09-09","arxiv_id":"2209.04121","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google/neural-tangents","insuhan/ntk_activations"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"feature-selection-with-gradient-descent-on","title":"Feature selection with gradient descent on two-layer networks in low-rotation regimes","date":"2022-08-04","arxiv_id":"2208.02789","n_code_links":0,"syntology":null},{"paper":"/paper/single-model-uncertainty-estimation-via","slug":"single-model-uncertainty-estimation-via","title":"Single Model Uncertainty Estimation via Stochastic Data Centering","date":"2022-07-14","arxiv_id":"2207.07235","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["llnl/deltauq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/out-of-distribution-detection-via-neural","slug":"out-of-distribution-detection-via-neural","title":"Out of Distribution Detection via Neural Network Anchoring","date":"2022-07-08","arxiv_id":"2207.04125","n_code_links":3,"syntology":null},{"paper":"/paper/neural-stein-critics-with-staged-l-2","slug":"neural-stein-critics-with-staged-l-2","title":"Neural Stein critics with staged $L^2$-regularization","date":"2022-07-07","arxiv_id":"2207.03406","n_code_links":1,"syntology":null},{"paper":null,"slug":"limitations-of-the-ntk-for-understanding","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","date":"2022-06-20","arxiv_id":"2206.10012","n_code_links":0,"syntology":null},{"paper":"/paper/fast-finite-width-neural-tangent-kernel-1","slug":"fast-finite-width-neural-tangent-kernel-1","title":"Fast Finite Width Neural Tangent Kernel","date":"2022-06-17","arxiv_id":"2206.08720","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google/neural-tangents","iclr2022anon/fast_finite_width_ntk"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"neural-tangent-kernel-analysis-of-shallow-a","title":"Large-width asymptotics for ReLU neural networks with $α$-Stable initializations","date":"2022-06-16","arxiv_id":"2206.08065","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-quantization-improves-generalization-ntk","title":"Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks","date":"2022-06-13","arxiv_id":"2206.05916","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-good-directions-to-escape-the-ntk","slug":"identifying-good-directions-to-escape-the-ntk","title":"Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials","date":"2022-06-08","arxiv_id":"2206.03688","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-generalization-power-of-the-overfitted","title":"On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model","date":"2022-06-04","arxiv_id":"2206.02047","n_code_links":0,"syntology":null},{"paper":"/paper/infinite-recommendation-networks-a-data","slug":"infinite-recommendation-networks-a-data","title":"Infinite Recommendation Networks: A Data-Centric Approach","date":"2022-06-03","arxiv_id":"2206.02626","n_code_links":5,"syntology":{"ran":8,"of":13,"n_ran_checked":6,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["noveens/distill_cf","noveens/infinite_ae_cf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"a-quadrature-perspective-on-frequency-bias-in","title":"Tuning Frequency Bias in Neural Network Training with Nonuniform Data","date":"2022-05-28","arxiv_id":"2205.14300","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neural-tangent-kernel-formula-for-ensembles","title":"Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel","date":"2022-05-25","arxiv_id":"2205.12904","n_code_links":0,"syntology":null},{"paper":null,"slug":"torchntk-a-library-for-calculation-of-neural","title":"TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models","date":"2022-05-24","arxiv_id":"2205.12372","n_code_links":0,"syntology":null},{"paper":null,"slug":"memorization-and-optimization-in-deep-neural","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","date":"2022-05-20","arxiv_id":"2205.10217","n_code_links":0,"syntology":null},{"paper":null,"slug":"mean-field-analysis-of-two-layer-neural-1","title":"Mean-Field Analysis of Two-Layer Neural Networks: Global Optimality with Linear Convergence Rates","date":"2022-05-19","arxiv_id":"2205.09860","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-consistent-dynamical-field-theory-of","title":"Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks","date":"2022-05-19","arxiv_id":"2205.09653","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-feature-learning-in-neural-networks-with","title":"On Feature Learning in Neural Networks with Global Convergence Guarantees","date":"2022-04-22","arxiv_id":"2204.10782","n_code_links":0,"syntology":null},{"paper":"/paper/generative-adversarial-method-based-on-neural","slug":"generative-adversarial-method-based-on-neural","title":"Single-level Adversarial Data Synthesis based on Neural Tangent Kernels","date":"2022-04-08","arxiv_id":"2204.04090","n_code_links":2,"syntology":null},{"paper":null,"slug":"neural-q-learning-for-solving-elliptic-pdes","title":"Neural Q-learning for solving PDEs","date":"2022-03-31","arxiv_id":"2203.17128","n_code_links":0,"syntology":null},{"paper":"/paper/demystifying-the-neural-tangent-kernel-from-a","slug":"demystifying-the-neural-tangent-kernel-from-a","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","date":"2022-03-28","arxiv_id":"2203.14577","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-neural-tangent-kernel-analysis-of","title":"On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks","date":"2022-03-27","arxiv_id":"2203.14328","n_code_links":0,"syntology":null},{"paper":"/paper/neural-tangent-kernel-analysis-of-deep-narrow","slug":"neural-tangent-kernel-analysis-of-deep-narrow","title":"Neural Tangent Kernel Analysis of Deep Narrow Neural Networks","date":"2022-02-07","arxiv_id":"2202.02981","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lthilnklover/deep-narrow-ntk"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tight-convergence-rate-bounds-for","title":"Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions","date":"2022-02-02","arxiv_id":"2202.00992","n_code_links":0,"syntology":null},{"paper":"/paper/neural-tangent-kernel-beyond-the-infinite","slug":"neural-tangent-kernel-beyond-the-infinite","title":"Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization","date":"2022-02-01","arxiv_id":"2202.00553","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mselezniova/ntk_beyond_limit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"implicit-bias-of-mse-gradient-optimization-in-1","title":"Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks","date":"2022-01-12","arxiv_id":"2201.04738","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-influence-functions-of-neural","title":"Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime","date":"2021-12-15","arxiv_id":"2112.08297","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-square-loss-in-training-1","title":"Understanding Square Loss in Training Overparametrized Neural Network Classifiers","date":"2021-12-07","arxiv_id":"2112.03657","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-graph-neural-tangent-kernel-via","title":"Fast Graph Neural Tangent Kernel via Kronecker Sketching","date":"2021-12-04","arxiv_id":"2112.02446","n_code_links":0,"syntology":null},{"paper":"/paper/a-structured-dictionary-perspective-on","slug":"a-structured-dictionary-perspective-on","title":"A Structured Dictionary Perspective on Implicit Neural Representations","date":"2021-12-03","arxiv_id":"2112.01917","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gortizji/inr_dictionaries"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"neural-tangent-kernel-of-matrix-product","title":"Neural Tangent Kernel of Matrix Product States: Convergence and Applications","date":"2021-11-28","arxiv_id":"2111.14046","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-equivalence-between-neural-network-and","slug":"on-the-equivalence-between-neural-network-and","title":"On the Equivalence between Neural Network and Support Vector Machine","date":"2021-11-11","arxiv_id":"2111.06063","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["leslie-ch/equiv-nn-svm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"new-insights-into-graph-convolutional","title":"New Insights into Graph Convolutional Networks using Neural Tangent Kernels","date":"2021-10-08","arxiv_id":"2110.04060","n_code_links":0,"syntology":null},{"paper":"/paper/neural-tangent-kernel-empowered-federated","slug":"neural-tangent-kernel-empowered-federated","title":"Neural Tangent Kernel Empowered Federated Learning","date":"2021-10-07","arxiv_id":"2110.03681","n_code_links":0,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":null}},{"paper":null,"slug":"efficient-computation-of-deep-nonlinear","title":"Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-feature-learning-in-shallow-and-multi","title":"On feature learning in shallow and multi-layer neural networks with global convergence guarantees","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"takeuchi-s-information-criteria-as","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-ntk-adversary-an-approach-to-adversarial","title":"The NTK Adversary: An Approach to Adversarial Attacks without any Model Access","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-curse-of-depth-in-kernel-regime","title":"The Curse of Depth in Kernel Regime","date":"2021-09-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deformed-semicircle-law-and-concentration-of","title":"Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks","date":"2021-09-20","arxiv_id":"2109.09304","n_code_links":0,"syntology":null},{"paper":"/paper/simple-fast-and-flexible-framework-for-matrix","slug":"simple-fast-and-flexible-framework-for-matrix","title":"Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks","date":"2021-07-31","arxiv_id":"2108.00131","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-networks-provably-classify-data-on","title":"Deep Networks Provably Classify Data on Curves","date":"2021-07-29","arxiv_id":"2107.14324","n_code_links":0,"syntology":null},{"paper":null,"slug":"stability-generalisation-of-gradient-descent","title":"Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel","date":"2021-07-27","arxiv_id":"2107.12723","n_code_links":0,"syntology":null},{"paper":"/paper/neural-contextual-bandits-without-regret","slug":"neural-contextual-bandits-without-regret","title":"Neural Contextual Bandits without Regret","date":"2021-07-07","arxiv_id":"2107.03144","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pkassraie/NNUCB"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-linear-networks-dynamics-low-rank-biases","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","date":"2021-06-30","arxiv_id":"2106.15933","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-dynamics-of-nonlinear","title":"Understanding Dynamics of Nonlinear Representation Learning and Its Application","date":"2021-06-28","arxiv_id":"2106.14836","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-convergence-of-deep-learning-with","slug":"on-the-convergence-of-deep-learning-with","title":"On the Convergence and Calibration of Deep Learning with Differential Privacy","date":"2021-06-15","arxiv_id":"2106.07830","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-neural-tangent-kernels-via-sketching","slug":"scaling-neural-tangent-kernels-via-sketching","title":"Scaling Neural Tangent Kernels via Sketching and Random Features","date":"2021-06-15","arxiv_id":"2106.07880","n_code_links":1,"syntology":null},{"paper":"/paper/what-can-linearized-neural-networks-actually","slug":"what-can-linearized-neural-networks-actually","title":"What can linearized neural networks actually say about generalization?","date":"2021-06-12","arxiv_id":"2106.06770","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gortizji/linearized-networks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dnn-based-topology-optimisation-spatial","slug":"dnn-based-topology-optimisation-spatial","title":"DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel","date":"2021-06-10","arxiv_id":"2106.05710","n_code_links":1,"syntology":null},{"paper":"/paper/neural-tangent-kernel-maximum-mean","slug":"neural-tangent-kernel-maximum-mean","title":"Neural Tangent Kernel Maximum Mean Discrepancy","date":"2021-06-06","arxiv_id":"2106.03227","n_code_links":1,"syntology":null},{"paper":"/paper/fundamental-tradeoffs-between-memorization","slug":"fundamental-tradeoffs-between-memorization","title":"Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimes","date":"2021-06-04","arxiv_id":"2106.02630","n_code_links":1,"syntology":null},{"paper":null,"slug":"rapid-feature-evolution-accelerates-learning","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","date":"2021-05-29","arxiv_id":"2105.14301","n_code_links":0,"syntology":null},{"paper":null,"slug":"properties-of-the-after-kernel","title":"Properties of the After Kernel","date":"2021-05-21","arxiv_id":"2105.10585","n_code_links":0,"syntology":null},{"paper":null,"slug":"tensor-programs-iib-architectural","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","date":"2021-05-08","arxiv_id":"2105.03703","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-pass-stochastic-gradient-descent-in","title":"One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks","date":"2021-05-01","arxiv_id":"2105.00262","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-shape-completion-via-deep-prior","title":"Unsupervised Shape Completion via Deep Prior in the Neural Tangent Kernel Perspective","date":"2021-04-19","arxiv_id":"2104.09023","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-recipe-for-global-convergence-guarantee-in","title":"A Recipe for Global Convergence Guarantee in Deep Neural Networks","date":"2021-04-12","arxiv_id":"2104.05785","n_code_links":0,"syntology":null},{"paper":"/paper/how-rotational-invariance-of-common-kernels","slug":"how-rotational-invariance-of-common-kernels","title":"How rotational invariance of common kernels prevents generalization in high dimensions","date":"2021-04-09","arxiv_id":"2104.04244","n_code_links":1,"syntology":null},{"paper":null,"slug":"spectral-analysis-of-the-neural-tangent","title":"Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks","date":"2021-04-07","arxiv_id":"2104.03093","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-features-for-the-neural-tangent-kernel","title":"Random Features for the Neural Tangent Kernel","date":"2021-04-03","arxiv_id":"2104.01351","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-with-neural-tangent-kernels-in-near","title":"Learning with Neural Tangent Kernels in Near Input Sparsity Time","date":"2021-04-01","arxiv_id":"2104.00415","n_code_links":0,"syntology":null},{"paper":"/paper/weighted-neural-tangent-kernel-a-generalized","slug":"weighted-neural-tangent-kernel-a-generalized","title":"Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel","date":"2021-03-22","arxiv_id":"2103.11558","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-generalization-power-of-overfitted-two","title":"On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models","date":"2021-03-09","arxiv_id":"2103.05243","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-learning-with-neural-tangent-kernels","title":"Meta-Learning with Neural Tangent Kernels","date":"2021-02-07","arxiv_id":"2102.03909","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-proof-of-global-convergence-of","title":"On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths","date":"2021-01-24","arxiv_id":"2101.09612","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-learning-in-reproducing-kernel-hilbert","title":"Meta-Learning in Reproducing Kernel Hilbert Space","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nngeometry-easy-and-fast-fisher-information","title":"NNGeometry: Easy and Fast Fisher Information Matrices and Neural Tangent Kernels in PyTorch","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"2012-11654","title":"Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks","date":"2020-12-21","arxiv_id":"2012.11654","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-eigenvector-bias-of-fourier-feature","slug":"on-the-eigenvector-bias-of-fourier-feature","title":"On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks","date":"2020-12-18","arxiv_id":"2012.10047","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-finite-neural-networks-can-we-trust","title":"Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?","date":"2020-12-08","arxiv_id":"2012.04477","n_code_links":0,"syntology":null},{"paper":"/paper/feature-learning-in-infinite-width-neural","slug":"feature-learning-in-infinite-width-neural","title":"Feature Learning in Infinite-Width Neural Networks","date":"2020-11-30","arxiv_id":"2011.14522","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["edwardjhu/TP4"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"deep-learning-versus-kernel-learning-an","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","date":"2020-10-28","arxiv_id":"2010.15110","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-lazy-training-for-over-parameterized","title":"Beyond Lazy Training for Over-parameterized Tensor Decomposition","date":"2020-10-22","arxiv_id":"2010.11356","n_code_links":0,"syntology":null},{"paper":"/paper/label-aware-neural-tangent-kernel-toward","slug":"label-aware-neural-tangent-kernel-toward","title":"Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity","date":"2020-10-22","arxiv_id":"2010.11775","n_code_links":1,"syntology":null},{"paper":"/paper/a-theoretical-analysis-of-catastrophic","slug":"a-theoretical-analysis-of-catastrophic","title":"A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix","date":"2020-10-07","arxiv_id":"2010.04003","n_code_links":2,"syntology":{"ran":7,"of":13,"n_ran_checked":7,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["tldoan/PCA-OGD"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamically-stable-infinite-width-limits-of-1","title":"Dynamically Stable Infinite-Width Limits of Neural Classifiers","date":"2020-09-28","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-the-outputs-of-finite-networks-1","title":"Predicting the Outputs of Finite Networks Trained with Noisy Gradients","date":"2020-09-28","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/kernel-based-smoothness-analysis-of-residual","slug":"kernel-based-smoothness-analysis-of-residual","title":"Kernel-Based Smoothness Analysis of Residual Networks","date":"2020-09-21","arxiv_id":"2009.10008","n_code_links":1,"syntology":null},{"paper":"/paper/self-adaptive-physics-informed-neural","slug":"self-adaptive-physics-informed-neural","title":"Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism","date":"2020-09-07","arxiv_id":"2009.04544","n_code_links":2,"syntology":null},{"paper":null,"slug":"deep-networks-and-the-multiple-manifold","title":"Deep Networks and the Multiple Manifold Problem","date":"2020-08-25","arxiv_id":"2008.11245","n_code_links":0,"syntology":null},{"paper":null,"slug":"finite-versus-infinite-neural-networks-an","title":"Finite Versus Infinite Neural Networks: an Empirical Study","date":"2020-07-31","arxiv_id":"2007.15801","n_code_links":0,"syntology":null},{"paper":"/paper/when-and-why-pinns-fail-to-train-a-neural","slug":"when-and-why-pinns-fail-to-train-a-neural","title":"When and why PINNs fail to train: A neural tangent kernel perspective","date":"2020-07-28","arxiv_id":"2007.14527","n_code_links":1,"syntology":null},{"paper":"/paper/compressing-invariant-manifolds-in-neural","slug":"compressing-invariant-manifolds-in-neural","title":"Geometric compression of invariant manifolds in neural nets","date":"2020-07-22","arxiv_id":"2007.11471","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mariogeiger/feature_lazy"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-an-understanding-of-residual-networks","title":"Towards an Understanding of Residual Networks Using Neural Tangent Hierarchy (NTH)","date":"2020-07-07","arxiv_id":"2007.03714","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-similarity-between-the-laplace-and","slug":"on-the-similarity-between-the-laplace-and","title":"On the Similarity between the Laplace and Neural Tangent Kernels","date":"2020-07-03","arxiv_id":"2007.01580","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"associative-memory-in-iterated","title":"Associative Memory in Iterated Overparameterized Sigmoid Autoencoders","date":"2020-06-30","arxiv_id":"2006.16540","n_code_links":0,"syntology":null},{"paper":"/paper/tensor-programs-ii-neural-tangent-kernel-for","slug":"tensor-programs-ii-neural-tangent-kernel-for","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","date":"2020-06-25","arxiv_id":"2006.14548","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-surprising-simplicity-of-the-early-time","title":"The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks","date":"2020-06-25","arxiv_id":"2006.14599","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-empirical-neural-tangent-kernel-of","title":"On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures","date":"2020-06-24","arxiv_id":"2006.13645","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-rates-for-averaged-stochastic","title":"Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime","date":"2020-06-22","arxiv_id":"2006.12297","n_code_links":0,"syntology":null},{"paper":"/paper/fourier-features-let-networks-learn-high","slug":"fourier-features-let-networks-learn-high","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","date":"2020-06-18","arxiv_id":"2006.10739","n_code_links":17,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tancik/fourier-feature-networks"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"collegial-ensembles","title":"Collegial Ensembles","date":"2020-06-13","arxiv_id":"2006.07678","n_code_links":0,"syntology":null},{"paper":"/paper/dynamically-stable-infinite-width-limits-of","slug":"dynamically-stable-infinite-width-limits-of","title":"Dynamically Stable Infinite-Width Limits of Neural Classifiers","date":"2020-06-11","arxiv_id":"2006.06574","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":11,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["deepmipt/research"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"bc91f98e564ed120754c6f268564932372083a170ce7e813d9420af311f2a425","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}