{"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":"/task/stochastic-optimization/papers/13","list_of":"/task/stochastic-optimization","task":"Stochastic Optimization","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":13,"pages_in_order":14,"rows_per_page":100,"rows":[1201,1300],"of":1387,"counts":{"archive_papers_tagged":1387,"with_a_code_link":337,"where_syntology_ran_a_sample":91,"not_listed_spam_title":0,"listed":1387,"listed_where_code_ran":91,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":75,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":75,"listed_every_run_a_failure_of_syntologys_instrument":16,"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":"/task/stochastic-optimization","prev":"/task/stochastic-optimization/papers/12","next":"/task/stochastic-optimization/papers/14","papers":[{"url":null,"slug":"stochastic-submodular-maximization-the-case","title":"Stochastic Submodular Maximization: The Case of Coverage Functions","date":"2017-11-05","arxiv_id":"1711.01566","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-variational-inference-for-fully","title":"Stochastic Variational Inference for Bayesian Sparse Gaussian Process Regression","date":"2017-11-01","arxiv_id":"1711.00221","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerate-rnn-based-training-with-importance","title":"Accelerate RNN-based Training with Importance Sampling","date":"2017-10-31","arxiv_id":"1711.00004","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-sampling-strategies-for-stochastic","title":"Adaptive Sampling Strategies for Stochastic Optimization","date":"2017-10-30","arxiv_id":"1710.11258","repositories_listed":0,"syntology":null},{"url":"/paper/gradient-sparsification-for-communication","slug":"gradient-sparsification-for-communication","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","date":"2017-10-26","arxiv_id":"1710.09854","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-reinforcement-learning","title":"Accelerated Reinforcement Learning","date":"2017-10-23","arxiv_id":"1710.08070","repositories_listed":0,"syntology":null},{"url":null,"slug":"function-norms-and-regularization-in-deep","title":"Function Norms and Regularization in Deep Networks","date":"2017-10-18","arxiv_id":"1710.06703","repositories_listed":0,"syntology":null},{"url":null,"slug":"convergence-diagnostics-for-stochastic","title":"Convergence diagnostics for stochastic gradient descent with constant step size","date":"2017-10-17","arxiv_id":"1710.06382","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-generative-model-for-single-cell-rna","title":"A deep generative model for single-cell RNA sequencing with application to detecting differentially expressed genes","date":"2017-10-13","arxiv_id":"1710.05086","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-online-learning-with-kernels","title":"Decentralized Online Learning with Kernels","date":"2017-10-11","arxiv_id":"1710.04062","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-nonconvex-optimization-with-large","title":"Stochastic Nonconvex Optimization with Large Minibatches","date":"2017-09-25","arxiv_id":"1709.08728","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-sgd-for-distributed-deep","title":"Accelerating SGD for Distributed Deep-Learning Using Approximated Hessian Matrix","date":"2017-09-15","arxiv_id":"1709.05069","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-modular-analysis-of-adaptive-non-convex","title":"A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds","date":"2017-09-08","arxiv_id":"1709.02726","repositories_listed":0,"syntology":null},{"url":null,"slug":"causality-aided-falsification","title":"Causality-Aided Falsification","date":"2017-09-08","arxiv_id":"1709.02555","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-convergence-analysis-for-a-class-of","title":"A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC","date":"2017-09-04","arxiv_id":"1709.01180","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-implicit-generative-models-using","title":"Learning Implicit Generative Models Using Differentiable Graph Tests","date":"2017-09-04","arxiv_id":"1709.01006","repositories_listed":0,"syntology":null},{"url":null,"slug":"hydroassets-portfolio-management-for-intraday","title":"Hydroassets Portfolio Management for Intraday Electricity Trading from a Discrete Time Stochastic Optimization Perspective","date":"2017-08-24","arxiv_id":"1508.05837","repositories_listed":0,"syntology":null},{"url":null,"slug":"weighted-parallel-sgd-for-distributed","title":"Weighted parallel SGD for distributed unbalanced-workload training system","date":"2017-08-16","arxiv_id":"1708.04801","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-stationary-stochastic-optimization-under","title":"Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures","date":"2017-08-09","arxiv_id":"1708.03020","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-optimization-with-bandit-sampling","title":"Stochastic Optimization with Bandit Sampling","date":"2017-08-08","arxiv_id":"1708.02544","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-guided-stochastic-searching","title":"Thompson Sampling Guided Stochastic Searching on the Line for Deceptive Environments with Applications to Root-Finding Problems","date":"2017-08-05","arxiv_id":"1708.01791","repositories_listed":0,"syntology":null},{"url":null,"slug":"follow-the-moving-leader-in-deep-learning","title":"Follow the Moving Leader in Deep Learning","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-convex-optimization-faster-local","title":"Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-stochastic-approximation-for-multi","title":"Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization","date":"2017-07-11","arxiv_id":"1707.03324","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-co-segmentation-in-3d-motion","title":"Temporal Action Co-Segmentation in 3D Motion Capture Data and Videos","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-analysis-of-stochastic-optimization","title":"A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints","date":"2017-06-25","arxiv_id":"1706.08141","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-optimization-of-finite-sums-with","title":"Improved Optimization of Finite Sums with Minibatch Stochastic Variance Reduced Proximal Iterations","date":"2017-06-21","arxiv_id":"1706.07001","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-approach-to-adaptive-regularization","title":"A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization","date":"2017-06-20","arxiv_id":"1706.06569","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-convergence-of-mirror-descent-beyond","title":"On the convergence of mirror descent beyond stochastic convex programming","date":"2017-06-18","arxiv_id":"1706.05681","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-reformulations-of-linear-systems","title":"Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory","date":"2017-06-04","arxiv_id":"1706.01108","repositories_listed":0,"syntology":null},{"url":null,"slug":"comments-on-the-proof-of-adaptive-submodular","title":"Comments on the proof of adaptive submodular function minimization","date":"2017-05-10","arxiv_id":"1705.03771","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-stochastic-gradient-descent-for","title":"Accelerating Stochastic Gradient Descent For Least Squares Regression","date":"2017-04-26","arxiv_id":"1704.08227","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-optimization-from-distributed","title":"Stochastic Optimization from Distributed, Streaming Data in Rate-limited Networks","date":"2017-04-25","arxiv_id":"1704.07888","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-limits-of-stochastic-sub-gradient","title":"Performance Limits of Stochastic Sub-Gradient Learning, Part II: Multi-Agent Case","date":"2017-04-20","arxiv_id":"1704.06025","repositories_listed":0,"syntology":null},{"url":null,"slug":"importance-sampled-stochastic-optimization","title":"Importance Sampled Stochastic Optimization for Variational Inference","date":"2017-04-19","arxiv_id":"1704.05786","repositories_listed":0,"syntology":null},{"url":null,"slug":"larger-is-better-the-effect-of-learning-rates","title":"Larger is Better: The Effect of Learning Rates Enjoyed by Stochastic Optimization with Progressive Variance Reduction","date":"2017-04-17","arxiv_id":"1704.04966","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-primal-dual-coordinate-method-with","title":"Stochastic Primal Dual Coordinate Method with Non-Uniform Sampling Based on Optimality Violations","date":"2017-03-21","arxiv_id":"1703.07056","repositories_listed":0,"syntology":null},{"url":null,"slug":"guaranteed-sufficient-decrease-for-variance","title":"Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent","date":"2017-03-20","arxiv_id":"1703.06807","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-statistical-model-error-into","title":"Incorporating statistical model error into the calculation of acceptability prices of contingent claims","date":"2017-03-16","arxiv_id":"1703.05709","repositories_listed":0,"syntology":null},{"url":null,"slug":"langevin-dynamics-with-continuous-tempering","title":"Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks","date":"2017-03-13","arxiv_id":"1703.04379","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-iterative-hard-thresholding-from-non","title":"Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization","date":"2017-03-01","arxiv_id":"1703.00119","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-optimize-neural-nets","title":"Learning to Optimize Neural Nets","date":"2017-03-01","arxiv_id":"1703.00441","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-rates-for-bandit-optimization-with-upper","title":"Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe","date":"2017-02-22","arxiv_id":"1702.06917","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-and-communication-efficient","title":"Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch-Prox","date":"2017-02-21","arxiv_id":"1702.06269","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-canonical-correlation-analysis","title":"Stochastic Canonical Correlation Analysis","date":"2017-02-21","arxiv_id":"1702.06533","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-distributed-synchronous-sgd-1","title":"Revisiting Distributed Synchronous SGD","date":"2017-02-19","arxiv_id":"1702.05800","repositories_listed":0,"syntology":null},{"url":null,"slug":"natasha-faster-non-convex-stochastic","title":"Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter","date":"2017-02-02","arxiv_id":"1702.00763","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-algorithms-for-1","title":"Communication-Efficient Algorithms for Decentralized and Stochastic Optimization","date":"2017-01-14","arxiv_id":"1701.03961","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-entropy-flow-networks","title":"Maximum Entropy Flow Networks","date":"2017-01-12","arxiv_id":"1701.03504","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-multidimensional-scaling","title":"Stochastic Multidimensional Scaling","date":"2016-12-21","arxiv_id":"1612.07089","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymptotic-optimality-in-stochastic","title":"Asymptotic Optimality in Stochastic Optimization","date":"2016-12-16","arxiv_id":"1612.05612","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-analysis-of-the-optimization-of","title":"An empirical analysis of the optimization of deep network loss surfaces","date":"2016-12-13","arxiv_id":"1612.04010","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-vs-each-approximation-to-softmax-for","title":"One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"without-replacement-sampling-for-stochastic-1","title":"Without-Replacement Sampling for Stochastic Gradient Methods","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-bayesian-learning-of-recurrent","title":"Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling","date":"2016-11-23","arxiv_id":"1611.08034","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-learning-for-stochastic-optimization","title":"Optimal Learning for Stochastic Optimization with Nonlinear Parametric Belief Models","date":"2016-11-22","arxiv_id":"1611.07161","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-connection-weights-in-neural","title":"Optimizing connection weights in neural networks using the whale optimization algorithm","date":"2016-11-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-adaptive-stochastic-optimization","title":"Scalable Adaptive Stochastic Optimization Using Random Projections","date":"2016-11-21","arxiv_id":"1611.06652","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-approximations-for-generalized","title":"Scalable Approximations for Generalized Linear Problems","date":"2016-11-21","arxiv_id":"1611.06686","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generalized-stochastic-variational-bayesian","title":"A Generalized Stochastic Variational Bayesian Hyperparameter Learning Framework for Sparse Spectrum Gaussian Process Regression","date":"2016-11-18","arxiv_id":"1611.06080","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-variational-inducing-input-gaussian","title":"Faster variational inducing input Gaussian process classification","date":"2016-11-18","arxiv_id":"1611.06132","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-asset-liability-management-problem-of-a","title":"The Asset Liability Management problem of a nuclear operator : a numerical stochastic optimization approach","date":"2016-11-15","arxiv_id":"1611.04877","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-untrusted-data","title":"Learning from Untrusted Data","date":"2016-11-07","arxiv_id":"1611.02315","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-stochastic-block-coordinate","title":"Asynchronous Stochastic Block Coordinate Descent with Variance Reduction","date":"2016-10-29","arxiv_id":"1610.09447","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistics-of-robust-optimization-a","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","date":"2016-10-11","arxiv_id":"1610.03425","repositories_listed":0,"syntology":null},{"url":null,"slug":"boost-k-means","title":"Boost K-Means","date":"2016-10-08","arxiv_id":"1610.02483","repositories_listed":0,"syntology":null},{"url":null,"slug":"exact-and-inexact-subsampled-newton-methods","title":"Exact and Inexact Subsampled Newton Methods for Optimization","date":"2016-09-27","arxiv_id":"1609.08502","repositories_listed":0,"syntology":null},{"url":null,"slug":"sooner-than-expected-hitting-the-wall-of","title":"Sooner than Expected: Hitting the Wall of Complexity in Evolution","date":"2016-09-25","arxiv_id":"1609.07722","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-vs-each-approximation-to-softmax-for-1","title":"One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities","date":"2016-09-23","arxiv_id":"1609.07410","repositories_listed":0,"syntology":null},{"url":null,"slug":"gray-box-inference-for-structured-gaussian","title":"Gray-box inference for structured Gaussian process models","date":"2016-09-14","arxiv_id":"1609.04289","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-heavy-ball","title":"Stochastic Heavy Ball","date":"2016-09-14","arxiv_id":"1609.04228","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-learning-of-multi-instance","title":"Stochastic Learning of Multi-Instance Dictionary for Earth Mover's Distance based Histogram Comparison","date":"2016-09-03","arxiv_id":"1609.00817","repositories_listed":0,"syntology":null},{"url":null,"slug":"doubly-stochastic-large-scale-kernel-learning","title":"Doubly stochastic large scale kernel learning with the empirical kernel map","date":"2016-09-02","arxiv_id":"1609.00585","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-dependent-convergence-for-distributed","title":"Data Dependent Convergence for Distributed Stochastic Optimization","date":"2016-08-30","arxiv_id":"1608.08337","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-structured-predictors-from-bandit","title":"Learning Structured Predictors from Bandit Feedback for Interactive NLP","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-quasi-newton-methods-for-nonconvex","title":"Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization","date":"2016-07-05","arxiv_id":"1607.01231","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-stochastic-subgradient-methods","title":"Accelerate Stochastic Subgradient Method by Leveraging Local Growth Condition","date":"2016-07-04","arxiv_id":"1607.01027","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-stochastic-optimization-via","title":"Distributed stochastic optimization via matrix exponential learning","date":"2016-06-03","arxiv_id":"1606.01190","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-weight-uncertainty-with-stochastic","title":"Learning Weight Uncertainty With Stochastic Gradient MCMC for Shape Classification","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-clustering-and-model-selection-1","title":"Simultaneous Clustering and Model Selection for Tensor Affinities","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-learning-rate-via-covariance-matrix","title":"Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks","date":"2016-05-31","arxiv_id":"1605.09593","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-optimization-for-large-scale","title":"Stochastic Optimization for Large-scale Optimal Transport","date":"2016-05-27","arxiv_id":"1605.08527","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-eigenvector-computation-via-shift-and","title":"Faster Eigenvector Computation via Shift-and-Invert Preconditioning","date":"2016-05-26","arxiv_id":"1605.08754","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-blind-source-separation-based-on","title":"Effective Blind Source Separation Based on the Adam Algorithm","date":"2016-05-25","arxiv_id":"1605.07833","repositories_listed":0,"syntology":null},{"url":null,"slug":"nestt-a-nonconvex-primal-dual-splitting","title":"NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization","date":"2016-05-25","arxiv_id":"1605.07747","repositories_listed":0,"syntology":null},{"url":null,"slug":"riemannian-svrg-fast-stochastic-optimization","title":"Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds","date":"2016-05-23","arxiv_id":"1605.07147","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-information-collecting-vehicle-routing","title":"The Information-Collecting Vehicle Routing Problem: Stochastic Optimization for Emergency Storm Response","date":"2016-05-18","arxiv_id":"1605.05711","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-the-model-order-of-deep-neural","title":"Reducing the Model Order of Deep Neural Networks Using Information Theory","date":"2016-05-16","arxiv_id":"1605.04859","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonconvex-sparse-learning-via-stochastic","title":"Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction","date":"2016-05-09","arxiv_id":"1605.02711","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-stochastic-optimization-for-deep","title":"Distributed stochastic optimization for deep learning (thesis)","date":"2016-05-07","arxiv_id":"1605.02216","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-for-stochastic-optimization-with","title":"Algorithms for stochastic optimization with functional or expectation constraints","date":"2016-04-13","arxiv_id":"1604.03887","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-globally-convergent-stochastic","title":"Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis","date":"2016-04-07","arxiv_id":"1604.01870","repositories_listed":0,"syntology":null},{"url":null,"slug":"katyusha-the-first-direct-acceleration-of","title":"Katyusha: The First Direct Acceleration of Stochastic Gradient Methods","date":"2016-03-18","arxiv_id":"1603.05953","repositories_listed":0,"syntology":null},{"url":null,"slug":"without-replacement-sampling-for-stochastic","title":"Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization","date":"2016-03-02","arxiv_id":"1603.00570","repositories_listed":0,"syntology":null},{"url":"/paper/scalable-metric-learning-via-weighted","slug":"scalable-metric-learning-via-weighted","title":"Scalable Metric Learning via Weighted Approximate Rank Component Analysis","date":"2016-03-01","arxiv_id":"1603.00370","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-dropout-for-shallow-and-deep","title":"Improved Dropout for Shallow and Deep Learning","date":"2016-02-06","arxiv_id":"1602.02220","repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-reduced-and-projection-free","title":"Variance-Reduced and Projection-Free Stochastic Optimization","date":"2016-02-05","arxiv_id":"1602.02101","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-distributed-sgd-with-variance","title":"Efficient Distributed SGD with Variance Reduction","date":"2015-12-09","arxiv_id":"1512.02970","repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-reduction-for-distributed-stochastic","title":"Variance Reduction for Distributed Stochastic Gradient Descent","date":"2015-12-05","arxiv_id":"1512.01708","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-projection-free-method-for-generalized","title":"A Projection Free Method for Generalized Eigenvalue Problem With a Nonsmooth Regularizer","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"7db1f64c8f8ba61b1b5805bead90238cc057f1a8e7bcde48a7ed1e8a527fbd17","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}