English
Related papers

Related papers: Autoregressive Learning in Joint KL: Sharp Oracle …

200 papers

Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different distributions (denoted as $\mu$ and $\mu'$, respectively). In this work, we give an…

Machine Learning · Computer Science 2020-05-20 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

In recent years, the robotics community has made substantial progress in robotic manipulation using deep reinforcement learning (RL). Effectively learning of long-horizon tasks remains a challenging topic. Typical RL-based methods…

Robotics · Computer Science 2021-05-13 Zhihao Li , Zhenglong Sun , Jionglong SU , Jiaming Zhang

Deep neural networks (DNNs) exhibit an exceptional capacity for generalization in practical applications. This work aims to capture the effect and benefits of depth for supervised learning via information-theoretic generalization bounds. We…

Machine Learning · Computer Science 2025-05-09 Haiyun He , Ziv Goldfeld

A loss function measures the discrepancy between the true values (observations) and their estimated fits, for a given instance of data. A loss function is said to be proper (unbiased, Fisher consistent) if the fits are defined over a unit…

Information Theory · Computer Science 2018-05-11 Amichai Painsky , Gregory W. Wornell

We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]),…

Machine Learning · Computer Science 2012-07-19 Mukund Narasimhan , Jeff A. Bilmes

Mutual Information (MI) is a fundamental measure of statistical dependence widely used in representation learning. While direct optimization of MI via its definition as a Kullback-Leibler divergence (KLD) is often intractable, many recent…

Machine Learning · Computer Science 2026-03-18 Reuben Dorent , Polina Golland , William Wells

When training autoregressive models to forecast dynamical systems, a critical question arises: how far into the future should the model be trained to predict? Too short a horizon may miss long-term trends, while too long a horizon can…

Machine Learning · Computer Science 2025-06-23 Pau Vilimelis Aceituno , Jack William Miller , Noah Marti , Youssef Farag , Victor Boussange

We consider learning in decentralized heterogeneous networks: agents seek to minimize a convex functional that aggregates data across the network, while only having access to their local data streams. We focus on the case where agents seek…

Optimization and Control · Mathematics 2021-06-02 Hrusikesha Pradhan , Amrit Singh Bedi , Alec Koppel , Ketan Rajawat

Autoregressive generation lies at the heart of the mechanism of large language models. It can be viewed as the repeated application of a next-token generator: starting from an input string (prompt), the generator is applied for $M$ steps,…

Machine Learning · Computer Science 2026-05-11 Ilan Doron-Arad , Idan Mehalel , Elchanan Mossel

Deep neural networks have demonstrated remarkable performance across numerous learning tasks but often suffer from miscalibration, resulting in unreliable probability outputs. This has inspired many recent works on mitigating…

Machine Learning · Computer Science 2025-09-23 Wenjian Huang , Guiping Cao , Jiahao Xia , Jingkun Chen , Hao Wang , Jianguo Zhang

Deploying Large Language Models (LLMs) on edge devices faces severe computational and memory constraints, limiting real-time processing and on-device intelligence. Hybrid architectures combining Structured State Space Models (SSMs) with…

Machine Learning · Computer Science 2026-04-16 Jason Kong , Nilesh Prasad Pandey , Flavio Ponzina , Tajana Rosing

Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have proven remarkably…

Machine Learning · Computer Science 2026-03-24 Haoqun Cao , Tengyang Xie

In this paper, we investigate the convergence of language models (LMs) trained under different random seeds, measuring convergence as the expected per-token Kullback--Leibler (KL) divergence across seeds. By comparing LM convergence as a…

Computation and Language · Computer Science 2025-10-01 Finlay Fehlauer , Kyle Mahowald , Tiago Pimentel

When and why representations learned by different deep neural networks are similar is an active research topic. We choose to address these questions from the perspective of identifiability theory, which suggests that a measure of…

Machine Learning · Computer Science 2025-10-20 Beatrix M. G. Nielsen , Emanuele Marconato , Andrea Dittadi , Luigi Gresele

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek KL divergence…

Machine Learning · Computer Science 2022-03-01 Parikshit Gopalan , Nina Narodytska , Omer Reingold , Vatsal Sharan , Udi Wieder

Motivated by the increasingly popular Score-based Generative Modeling (SGM), we study the Inexact Langevin Dynamics (ILD) and Inexact Langevin Algorithm (ILA) where a score function estimate is used in place of the exact score. We establish…

Machine Learning · Computer Science 2026-03-31 Kaylee Yingxi Yang , Andre Wibisono

Horizon reduction is a common design strategy in offline reinforcement learning (RL), used to mitigate long-horizon credit assignment, improve stability, and enable scalable learning through truncated rollouts, windowed training, or…

Machine Learning · Computer Science 2026-01-06 Uday Kumar Nidadala , Venkata Bhumika Guthi

In this paper, we derive a useful lower bound for the Kullback-Leibler divergence (KL-divergence) based on the Hammersley-Chapman-Robbins bound (HCRB). The HCRB states that the variance of an estimator is bounded from below by the…

Statistics Theory · Mathematics 2019-11-05 Tomohiro Nishiyama

Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward…

Machine Learning · Computer Science 2026-05-11 Lucas Monteiro Paes , Natalie Mackraz , Barry-John Theobald , Federico Danieli

Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, which implicitly assumes that the model generalizes similarly…

Machine Learning · Computer Science 2024-01-08 Firas Laakom , Yuheng Bu , Moncef Gabbouj