Methods › General › Momentum Rules › Demon
Demon
Introduced by John Chen et al. in Demon: Improved Neural Network Training with Momentum Decay
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Decaying Momentum, or Demon, is a stochastic optimizer motivated by decaying the total contribution of a gradient to all future updates. By decaying the momentum parameter, the total contribution of a gradient to all future updates is decayed. A particular gradient term gₜ contributes a total of η∑ᵢβⁱ of its "energy" to all future gradient updates, and this results in the geometric sum, ∑^∞ᵢ₌₁βⁱ = β∑^∞ᵢ₌₀βⁱ = β/(1-β). Decaying this sum results in the Demon algorithm. Letting βᵢₙᵢₜ be the initial β; then at the current step t with total T steps, the decay routine is given by solving the below for βₜ:
βₜ/(1-βₜ) = (1-t/T)βᵢₙᵢₜ/(1-βᵢₙᵢₜ)
Where (1-t/T) refers to the proportion of iterations remaining. Note that Demon typically requires no hyperparameter tuning as it is usually decayed to 0 or a small negative value at time T. Improved performance is observed by delaying the decaying. Demon can be applied to any gradient descent algorithm with a momentum parameter.
In Syntology about another paper, arXiv:2308.04152: harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2308.04152'). Repositories: 2 listed of 2 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2308.04152, not a method entry. About another paper: this answer is about arXiv:2308.04152, while the archive credits arXiv:1910.04952.
From the lookup's note on this name: The same name also belongs to the paper “DeMoN: Depth and Motion Network for Learning Monocular Stereo” (arXiv:1612.02401, 751 citations), which the lookup finds cited far more than the paper this answer is about (98 citations), so this answer may be about a different sense of the name. For arXiv:1612.02401: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2308.04152 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 1 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 16 · with a code link: 5 · where Syntology ran a sample: 2 (0 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 16 tagged: 0 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 16 of 16, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Representation and Interpretation in Artificial and Natural Computing 14 Feb 2025 · 0 repositories · arXiv:2502.10383
-
DEMONet: Underwater Acoustic Target Recognition based on Multi-Expert Network and Cross-Temporal Variational Autoencoder 5 Nov 2024 · 0 repositories · arXiv:2411.02758
-
Training-free Diffusion Model Alignment with Sampling Demons 8 Oct 2024 · 1 repository · arXiv:2410.05760Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
Neural Entropy 5 Sep 2024 · 0 repositories · arXiv:2409.03817
-
Str-L Pose: Integrating Point and Structured Line for Relative Pose Estimation in Dual-Graph 28 Aug 2024 · 0 repositories · arXiv:2408.15750
-
A Decentralized and Self-Adaptive Approach for Monitoring Volatile Edge Environments 13 May 2024 · 1 repository · arXiv:2405.07806
-
Reflective Linguistic Programming (RLP): A Stepping Stone in Socially-Aware AGI (SocialAGI) 22 May 2023 · 0 repositories · arXiv:2305.12647
-
How to train your demon to do fast information erasure without heat production 17 May 2023 · 0 repositories · arXiv:2305.10607
-
Thermodynamic AI and the fluctuation frontier 9 Feb 2023 · 0 repositories · arXiv:2302.06584
-
Differentiable Neural Computers with Memory Demon 5 Nov 2022 · 1 repository · arXiv:2211.02987Syntology official (archive's flag): 3 ran · 3 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; 3 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
Static Knowledge vs. Dynamic Argumentation: A Dual Theory Based on Kripke Semantics 27 Sep 2022 · 0 repositories · arXiv:2209.13082
-
Boosting Adversarial Transferability of MLP-Mixer 26 Apr 2022 · 0 repositories · arXiv:2204.12204
-
Learning Relational Rules from Rewards 25 Mar 2022 · 1 repository · arXiv:2203.13599
-
Nonequilibrium thermodynamics of self-supervised learning 16 Jun 2021 · 0 repositories · arXiv:2106.08981
-
Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty 16 Apr 2021 · 0 repositories · arXiv:2104.08278
-
Demon: Improved Neural Network Training with Momentum Decay 11 Oct 2019 · 2 repositories · arXiv:1910.04952
Tasks archive 2025-07-28
18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections