English
Related papers

Related papers: Conformal Symplectic Optimization for Stable Reinf…

200 papers

This work proposes a unified control architecture that couples a Reinforcement Learning (RL)-driven controller with a disturbance-rejection Extended State Observer (ESO), complemented by an Event-Triggered Mechanism (ETM) to limit…

Optimization and Control · Mathematics 2026-01-01 Ningwei Bai , Chi Pui Chan , Qichen Yin , Tengyang Gong , Yunda Yan , Zezhi Tang

Generalization analyses of deep learning typically assume that the training converges to a fixed point. But, recent results indicate that in practice, the weights of deep neural networks optimized with stochastic gradient descent often…

Machine Learning · Computer Science 2022-08-22 Nisha Chandramoorthy , Andreas Loukas , Khashayar Gatmiry , Stefanie Jegelka

The performance of an optimizer on large-scale deep learning models depends critically on fine-tuning the learning rate, often requiring an extensive grid search over base learning rates, schedules, and other hyperparameters. In this paper,…

Machine Learning · Computer Science 2025-06-11 Ruichen Jiang , Ali Kavis , Aryan Mokhtari

Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse…

Robotics · Computer Science 2020-02-28 Ke Lin , Liang Gong , Xudong Li , Te Sun , Binhao Chen , Chengliang Liu , Zhengfeng Zhang , Jian Pu , Junping Zhang

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Machine Learning · Computer Science 2024-02-06 Xinglong Zhang , Yaoqian Peng , Biao Luo , Wei Pan , Xin Xu , Haibin Xie

We present Re-weighted Gradient Descent (RGD), a novel optimization technique that improves the performance of deep neural networks through dynamic sample re-weighting. Leveraging insights from distributionally robust optimization (DRO)…

Machine Learning · Computer Science 2024-10-15 Ramnath Kumar , Kushal Majmundar , Dheeraj Nagaraj , Arun Sai Suggala

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Machine Learning · Computer Science 2025-10-07 Lianghuan Huang , Sagnik Anupam , Insup Lee , Shuo Li , Osbert Bastani

Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts, supporting reliable decision-making in complex, multi-agent environments. However,…

Machine Learning · Statistics 2025-08-26 Yannis Montreuil , Axel Carlier , Lai Xing Ng , Wei Tsang Ooi

We introduce AdaAct, a novel optimization algorithm that adjusts learning rates according to activation variance. Our method enhances the stability of neuron outputs by incorporating neuron-wise adaptivity during the training process, which…

Machine Learning · Computer Science 2025-06-11 Hyunseok Seung , Jaewoo Lee , Hyunsuk Ko

Training deep neural networks is challenging. To accelerate training and enhance performance, we propose PadamP, a novel optimization algorithm. PadamP is derived by applying the adaptive estimation of the p-th power of the second-order…

Optimization and Control · Mathematics 2025-03-14 Yongqi Li , Xiaowei Zhang

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Machine Learning · Computer Science 2025-06-24 Ju-Seung Byun , Andrew Perrault

In neural network training, RMSProp and Adam remain widely favoured optimisation algorithms. One of the keys to their performance lies in selecting the correct step size, which can significantly influence their effectiveness. Additionally,…

Machine Learning · Computer Science 2024-04-05 Alokendu Mazumder , Rishabh Sabharwal , Manan Tayal , Bhartendu Kumar , Punit Rathore

Stochastic gradient descent (SGD) and its many variants are the widespread optimization algorithms for training deep neural networks. However, SGD suffers from inevitable drawbacks, including vanishing gradients, lack of theoretical…

Machine Learning · Computer Science 2024-01-09 Zeinab Ebrahimi , Gustavo Batista , Mohammad Deghat

Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to adjust the performance of AI agents to meet human…

Machine Learning · Computer Science 2025-06-23 Tsunehiko Tanaka , Kenshi Abe , Kaito Ariu , Tetsuro Morimura , Edgar Simo-Serra

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

This paper investigates the partial linear model by Least Absolute Deviation (LAD) regression. We parameterize the nonparametric term using Deep Neural Networks (DNNs) and formulate a penalized LAD problem for estimation. Specifically, our…

Machine Learning · Statistics 2025-11-27 Lechen Feng , Haoran Li , Lucky Li , Xingqiu Zhao

Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formulations, however, are more difficult to solve. We therefore…

Machine Learning · Statistics 2020-11-03 Soumyadip Ghosh , Mark Squillante , Ebisa Wollega

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…

Machine Learning · Computer Science 2021-01-29 Sobhan Miryoosefi , Kianté Brantley , Hal Daumé , Miroslav Dudik , Robert Schapire

The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear…

Machine Learning · Computer Science 2021-06-21 John D. Martin , Joseph Modayil

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic…