English
Related papers

Related papers: Recursive KL Divergence Optimization: A Dynamic Fr…

200 papers

Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In…

Machine Learning · Computer Science 2022-02-01 Hao Liu , Huaping Liu

The Information Contrastive (I-Con) framework revealed that over 23 representation learning methods implicitly minimize KL divergence between data and learned distributions that encode similarities between data points. However, a KL-based…

Machine Learning · Computer Science 2025-12-05 Jasmine Shone , Zhening Li , Shaden Alshammari , Mark Hamilton , William Freeman

Decision-focused learning (DFL) has emerged as a powerful end-to-end alternative to conventional predict-then-optimize (PTO) pipelines by directly optimizing predictive models through downstream decision losses. Existing DFL frameworks are…

Machine Learning · Computer Science 2025-12-01 Xinyu Wang , Jinxiao Du , Yiyang Peng , Wei Ma

As the field of representation learning grows, there has been a proliferation of different loss functions to solve different classes of problems. We introduce a single information-theoretic equation that generalizes a large collection of…

Machine Learning · Computer Science 2025-04-24 Shaden Alshammari , John Hershey , Axel Feldmann , William T. Freeman , Mark Hamilton

Reinforcement learning (RL) in continuous state-action spaces remains challenging in scientific computing due to poor sample efficiency and lack of pathwise physical consistency. We introduce Differential Reinforcement Learning…

Machine Learning · Computer Science 2026-02-06 Minh Nguyen , Chandrajit Bajaj

The probabilistic diffusion model (DM), generating content by inferencing through a recursive chain structure, has emerged as a powerful framework for visual generation. After pre-training on enormous data, the model needs to be properly…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Tao Ren , Zishi Zhang , Jingyang Jiang , Zehao Li , Shentao Qin , Yi Zheng , Guanghao Li , Qianyou Sun , Yan Li , Jiafeng Liang , Xinping Li , Yijie Peng

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

This paper presents a framework to tackle constrained combinatorial optimization problems using deep Reinforcement Learning (RL). To this end, we extend the Neural Combinatorial Optimization (NCO) theory in order to deal with constraints in…

Machine Learning · Computer Science 2020-06-23 Ruben Solozabal , Josu Ceberio , Martin Takáč

We propose a novel contrastive learning framework to effectively address the challenges of data heterogeneity in federated learning. We first analyze the inconsistency of gradient updates across clients during local training and establish…

Machine Learning · Computer Science 2024-06-03 Seonguk Seo , Jinkyu Kim , Geeho Kim , Bohyung Han

This paper addresses a new interpretation of the traditional optimization method in reinforcement learning (RL) as optimization problems using reverse Kullback-Leibler (KL) divergence, and derives a new optimization method using forward KL…

Machine Learning · Computer Science 2022-04-25 Taisuke Kobayashi

This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in…

Machine Learning · Computer Science 2024-05-02 Wei Xiong , Hanze Dong , Chenlu Ye , Ziqi Wang , Han Zhong , Heng Ji , Nan Jiang , Tong Zhang

Large Language Models (LLMs) tend to respond correctly to prompts that align well with the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failures, especially on…

Machine Learning · Computer Science 2026-05-12 Yeping Jin , Jiaming Hu , Ioannis Ch. Paschalidis

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

Optimization and Control · Mathematics 2024-01-04 Daokuan Zhu , Tianqi Xu , Jie Lu

We propose kernel distributionally robust optimization (Kernel DRO) using insights from the robust optimization theory and functional analysis. Our method uses reproducing kernel Hilbert spaces (RKHS) to construct a wide range of convex…

Optimization and Control · Mathematics 2021-06-28 Jia-Jie Zhu , Wittawat Jitkrittum , Moritz Diehl , Bernhard Schölkopf

We introduce a principled learning to optimize (L2O) framework for solving fixed-point problems involving general nonexpansive mappings. Our idea is to deliberately inject summable perturbations into a standard Krasnosel'skii-Mann iteration…

Systems and Control · Electrical Eng. & Systems 2026-01-13 Andrea Martin , Giuseppe Belgioioso

Learning-to-optimize (L2O) is an emerging research area in large-scale optimization with applications in data science. Recently, researchers have proposed a novel L2O framework called learned mirror descent (LMD), based on the classical…

Optimization and Control · Mathematics 2024-05-13 Hong Ye Tan , Subhadip Mukherjee , Junqi Tang , Carola-Bibiane Schönlieb

Recursion is the fundamental paradigm to finitely describe potentially infinite objects. As state-of-the-art reinforcement learning (RL) algorithms cannot directly reason about recursion, they must rely on the practitioner's ingenuity in…

Machine Learning · Computer Science 2022-06-24 Ernst Moritz Hahn , Mateo Perez , Sven Schewe , Fabio Somenzi , Ashutosh Trivedi , Dominik Wojtczak

Distributionally Robust Optimization (DRO) has enabled to prove the equivalence between robustness and regularization in classification and regression, thus providing an analytical reason why regularization generalizes well in statistical…

Optimization and Control · Mathematics 2020-07-15 Esther Derman , Shie Mannor

Dense retrieval models use bi-encoder network architectures for learning query and document representations. These representations are often in the form of a vector representation and their similarities are often computed using the dot…

Information Retrieval · Computer Science 2023-05-01 Hamed Zamani , Michael Bendersky

Contrastive learning is an efficient approach to self-supervised representation learning. Although recent studies have made progress in the theoretical understanding of contrastive learning, the investigation of how to characterize the…

Machine Learning · Computer Science 2023-08-21 Hiroki Waida , Yuichiro Wada , Léo Andéol , Takumi Nakagawa , Yuhui Zhang , Takafumi Kanamori
‹ Prev 1 2 3 10 Next ›