English
Related papers

Related papers: Fighting Uncertainty with Gradients: Offline Reinf…

200 papers

We study the performance of stochastic first-order methods for finding saddle points of convex-concave functions. A notorious challenge faced by such methods is that the gradients can grow arbitrarily large during optimization, which may…

Machine Learning · Computer Science 2024-06-10 Gergely Neu , Nneka Okolo

Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in high-stakes…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Dipkamal Bhusal , Md Tanvirul Alam , Nidhi Rastogi

Learning with noisy labels is an important topic for scalable training in many real-world scenarios. However, few previous research considers this problem in the online setting, where the arrival of data is streaming. In this paper, we…

Machine Learning · Computer Science 2023-06-09 Yifan Yang , Alec Koppel , Zheng Zhang

Evaluating and optimizing policies in the presence of unobserved confounders is a problem of growing interest in offline reinforcement learning. Using conventional methods for offline RL in the presence of confounding can not only lead to…

Machine Learning · Statistics 2023-11-08 Chinmaya Kausik , Yangyi Lu , Kevin Tan , Maggie Makar , Yixin Wang , Ambuj Tewari

As deep learning models and datasets rapidly scale up, network training is extremely time-consuming and resource-costly. Instead of training on the entire dataset, learning with a small synthetic dataset becomes an efficient solution.…

Machine Learning · Computer Science 2022-08-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , David Z. Pan

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

There is growing interest in reinforcement learning (RL) methods that leverage the simulator's derivatives to improve learning efficiency. While early gradient-based approaches have demonstrated superior performance compared to…

Robotics · Computer Science 2025-09-05 Joseph Amigo , Rooholla Khorrambakht , Elliot Chane-Sane , Nicolas Mansard , Ludovic Righetti

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Jie Liu , Gongye Liu , Jiajun Liang , Yangguang Li , Jiaheng Liu , Xintao Wang , Pengfei Wan , Di Zhang , Wanli Ouyang

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…

Machine Learning · Computer Science 2021-02-12 Mengjiao Yang , Ofir Nachum

Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the…

Machine Learning · Computer Science 2023-06-06 Amirhossein Reisizadeh , Haochuan Li , Subhro Das , Ali Jadbabaie

A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In this work, we unlock a gradient-based…

Machine Learning · Statistics 2025-03-19 Logan Engstrom , Andrew Ilyas , Benjamin Chen , Axel Feldmann , William Moses , Aleksander Madry

This work considers the problem of decentralized online learning, where the goal is to track the optimum of the sum of time-varying functions, distributed across several nodes in a network. The local availability of the functions and their…

Machine Learning · Computer Science 2024-02-14 Shivangi Dubey Sharma , Ketan Rajawat

One approach for reducing run time and improving efficiency of machine learning is to reduce the convergence rate of the optimization algorithm used. Shuffling is an algorithm technique that is widely used in machine learning, but it only…

Machine Learning · Computer Science 2023-06-29 Yuetong Xu , Baharan Mirzasoleiman

The packing problem, also known as cutting or nesting, has diverse applications in logistics, manufacturing, layout design, and atlas generation. It involves arranging irregularly shaped pieces to minimize waste while avoiding overlap.…

Machine Learning · Computer Science 2023-11-01 Tianyang Xue , Mingdong Wu , Lin Lu , Haoxuan Wang , Hao Dong , Baoquan Chen

Stochastic optimization problems with unknown decision-dependent distributions have attracted increasing attention in recent years due to its importance in applications. Since the gradient of the objective function is inaccessible as a…

Optimization and Control · Mathematics 2025-10-30 Yuya Hikima , Akiko Takeda

First-order algorithms have been popular for solving convex and non-convex optimization problems. A key assumption for the majority of these algorithms is that the gradient of the objective function is globally Lipschitz continuous, but…

Optimization and Control · Mathematics 2024-02-07 Junyu Zhang , Mingyi Hong

Pairwise learning is essential in machine learning, especially for problems involving loss functions defined on pairs of training examples. Online gradient descent (OGD) algorithms have been proposed to handle online pairwise learning,…

Machine Learning · Computer Science 2023-10-11 Hilal AlQuabeh , Bhaskar Mukhoty , Bin Gu

Motion planning under uncertainty is one of the main challenges in developing autonomous driving vehicles. In this work, we focus on the uncertainty in sensing and perception, resulted from a limited field of view, occlusions, and sensing…

Robotics · Computer Science 2021-10-05 Kasra Rezaee , Peyman Yadmellat , Simon Chamorro

We consider a natural model of online preference aggregation, where sets of preferred items $R_1, R_2, \ldots, R_t$ along with a demand for $k_t$ items in each $R_t$, appear online. Without prior knowledge of $(R_t, k_t)$, the learner…

Machine Learning · Computer Science 2020-11-06 Dimitris Fotakis , Thanasis Lianeas , Georgios Piliouras , Stratis Skoulakis