English
Related papers

Related papers: Neural Sequence Model Training via $\alpha$-diverg…

200 papers

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearized losses on large…

Machine Learning · Computer Science 2019-03-12 Weiran Wang , Nathan Srebro

With the increasing need for handling large state and action spaces, general function approximation has become a key technique in reinforcement learning (RL). In this paper, we propose a general framework that unifies model-based and…

Machine Learning · Computer Science 2022-10-03 Zixiang Chen , Chris Junchi Li , Angela Yuan , Quanquan Gu , Michael I. Jordan

State-of-the-art neural networks can be trained to become remarkable solutions to many problems. But while these architectures can express symbolic, perfect solutions, trained models often arrive at approximations instead. We show that the…

Machine Learning · Computer Science 2025-09-09 Matan Abudy , Orr Well , Emmanuel Chemla , Roni Katzir , Nur Lan

Function regression/approximation is a fundamental application of machine learning. Neural networks (NNs) can be easily trained for function regression using a sufficient number of neurons and epochs. The forward-forward learning algorithm…

Machine Learning · Computer Science 2025-10-16 Shivam Padmani , Akshay Joshi

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of…

Machine Learning · Computer Science 2020-02-17 Louis Kirsch , Sjoerd van Steenkiste , Jürgen Schmidhuber

We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by…

Machine Learning · Computer Science 2020-05-05 Raviteja Anantha , Stephen Pulman , Srinivas Chappidi

In this paper, we propose a machine learning (ML) method to learn how to solve a generic constrained continuous optimization problem. To the best of our knowledge, the generic methods that learn to optimize, focus on unconstrained…

Machine Learning · Computer Science 2021-01-05 Seyedrazieh Bayati , Faramarz Jabbarvaziri

Classical supervised learning via empirical risk (or negative log-likelihood) minimization hinges upon the assumption that the testing distribution coincides with the training distribution. This assumption can be challenged in modern…

Optimization and Control · Mathematics 2020-10-02 Yassine Laguel , Jérôme Malick , Zaid Harchaoui

Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterintuitive phenomena have been reported in LLMs, exhibiting…

Machine Learning · Computer Science 2025-09-03 Haoze Wu , Cheng Wang , Wenshuo Zhao , Junxian He

We study inverse optimization (IO), where the goal is to use a parametric optimization program as the hypothesis class to infer relationships between input-decision pairs. Most of the literature focuses on learning only the objective…

Optimization and Control · Mathematics 2025-05-22 Ke Ren , Peyman Mohajerin Esfahani , Angelos Georghiou

We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probability measures over the weight parameters associated with…

Machine Learning · Computer Science 2022-10-19 Jingwei Zhang , Xunpeng Huang , Jincheng Yu

Hindsight goal relabeling has become a foundational technique in multi-goal reinforcement learning (RL). The essential idea is that any trajectory can be seen as a sub-optimal demonstration for reaching its final state. Intuitively,…

Machine Learning · Computer Science 2023-01-31 Lunjun Zhang , Bradly C. Stadie

Many important computer vision tasks are naturally formulated to have a non-differentiable objective. Therefore, the standard, dominant training procedure of a neural network is not applicable since back-propagation requires the gradients…

Computer Vision and Pattern Recognition · Computer Science 2023-05-04 Yash Patel

The key task of machine learning is to minimize the loss function that measures the model fit to the training data. The numerical methods to do this efficiently depend on the properties of the loss function. The most decisive among these…

Machine Learning · Computer Science 2025-10-31 Tomas Hrycej , Bernhard Bermeitinger , Massimo Pavone , Götz-Henrik Wiegand , Siegfried Handschuh

The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that…

Machine Learning · Computer Science 2025-06-27 Ruiyang Hong , Anastasis Kratsios

To date, the multi-objective optimization literature has mainly focused on conflicting objectives, studying the Pareto front, or requiring users to balance tradeoffs. Yet, in machine learning practice, there are many scenarios where such…

Machine Learning · Computer Science 2025-03-05 Yonathan Efroni , Ben Kretzu , Daniel Jiang , Jalaj Bhandari , Zheqing , Zhu , Karen Ullrich

We develop minimax optimal risk bounds for the general learning task consisting in predicting as well as the best function in a reference set $\mathcal{G}$ up to the smallest possible additive term, called the convergence rate. When the…

Statistics Theory · Mathematics 2009-09-09 Jean-Yves Audibert

Decision-Focused Learning (DFL) is an emerging learning paradigm that tackles the task of training a machine learning (ML) model to predict missing parameters of an incomplete optimization problem, where the missing parameters are…

Machine Learning · Computer Science 2025-06-23 Yehya Farhat

Despite the empirical success of meta reinforcement learning (meta-RL), there are still a number poorly-understood discrepancies between theory and practice. Critically, biased gradient estimates are almost always implemented in practice,…

Machine Learning · Computer Science 2021-12-15 Yunhao Tang

The paper proposes a novel regularization procedure for machine learning. The proposed high-order regularization (HR) provides new insight into regularization, which is widely used to train a neural network that can be utilized to…

Machine Learning · Computer Science 2025-05-14 Xinghua Liu , Ming Cao