paper-with-me

Papers

Conformal Symplectic and Relativistic Optimization

2019-03-11 · NeurIPS 2020 12 · Guilherme França, Jeremias Sulam, Daniel P. Robinson, René Vidal

Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order differential equation with friction. Such connections with continuous-time dynamical systems have been instrumental in demystifying acceleration phenomena in optimization. Here we study structure-preserving discretizations for a certain class of dissipative (conformal) Hamiltonian systems, allowing us to analyze the symplectic structure of both Nesterov and heavy ball, besides providing several new insights into these methods. Moreover, we propose a new algorithm based on a dissipative relativistic system that normalizes the momentum and may result in more stable/faster optimization. Importantly, such a method generalizes both Nesterov and heavy ball, each being recovered as distinct limiting cases, and has potential advantages at no additional cost.

📄 PDF Abstract BibTeX arXiv:1903.04100

Code (1)

guisf/rgd 공식 구현

Tasks

Friction

Similar Papers 제목 키워드 기반

Conformal Symplectic Optimization for Stable Reinforcement Learning

2024-12-03 · Yao Lyu, Xiangteng Zhang, Shengbo Eben Li, Jingliang Duan 외

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-ins…

Atari GamesDeep Reinforcement Learningreinforcement-learningReinforcement Learning+2

CoSynFlow: Conformal Symplectic Neural Flows for Cross-System Prediction of Dissipative Hamiltonian Dynamics

2026-08-01 · Baige Xu, Takaharu Yaguchi arxiv

Learning solution operators for differential equations is a central problem in scientific machine learning. However, many neural operator methods optimize prediction accuracy without explicitly enforcing the geometric st…

CSympNet-ID: conformal-symplectic map learning for linearly damped Hamiltonian systems

2026-07-03 · Jiale Gong, Pengzhan Jin, Dongyang Kuang, Lu Li 외 arxiv

Learning dissipative dynamics from discrete observations is essential for reliable long-horizon prediction and physically meaningful parameter identification. For linearly damped Hamiltonian systems, the exact flow is ge…

Conformal models for hypercolumns in the primary visual cortex V1

2024-10-26 · D. V. Alekseevsky, A. Spiro

We propose a differential geometric model of hypercolumns in the primary visual cortex V1 that combines features of the symplectic model of the primary visual cortex by A. Sarti, G. Citti and J. Petitot and of the spheri…

CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning

2026-03-02 · Pratik Jawahar, Maurizio Pierini arxiv

Current deep learning primitives dealing with temporal dynamics suffer from a fundamental dichotomy: they are either discrete and unstable (LSTMs) \citep{pascanu_difficulty_2013}, leading to exploding or vanishing gradie…