SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
International Conference on Machine Learning , pages=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Evolutionary game theory shows gradient descent and stochastic gradient descent drive neural networks to distinct stable states favoring shortcut or core subnetworks, with data and optimization noise shaping shortcut bias formation.
Introduces a margin-adaptive confidence ranking method that learns an estimator from simulated diversity and derives margin-dependent generalization bounds for use in fixed-sequence testing of LLM-human agreement.
citing papers explorer
-
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
-
Deciphering Shortcut Learning from an Evolutionary Game Theory Perspective
Evolutionary game theory shows gradient descent and stochastic gradient descent drive neural networks to distinct stable states favoring shortcut or core subnetworks, with data and optimization noise shaping shortcut bias formation.
-
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
Introduces a margin-adaptive confidence ranking method that learns an estimator from simulated diversity and derives margin-dependent generalization bounds for use in fixed-sequence testing of LLM-human agreement.
- Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training