Kullback-Leibler Divergence

Follow this topic Ask about this topic

Recent momentum

+57%

11 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Kullback-Leibler Divergence.

Period ending 2026-09-14

7 new papers

A weekly snapshot of new work published in Kullback-Leibler Divergence.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Kullback-Leibler Divergence.

102 papers

Latest in Kullback-Leibler Divergence

Browse all topics →

Fast Rates for Inverse Reinforcement Learning
May 14, 2026Andreas Schlaginhaufen, Maryam KamgarpourEntropy Regularized Reinforcement Learning Kullback-Leibler Divergence
On the Generalization of Knowledge Distillation: An Information-Theoretic View
May 13, 2026Bingying Li, Haiyun HeKnowledge Distillation Ontology-Amplified Distillation
Lost and Found in Translation: Variational Diagnostics for Neural Codebook Channels
May 13, 2026Yusuke HayashiVariational Autoencoder Codebooks
Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
May 12, 2026Yunbei Xu, Yuzhe Yuan, Ruohan ZhanKullback-Leibler Divergence Autoregressive Model
Information theoretic underpinning of self-supervised learning by clustering
May 12, 2026Josef Kittler, Sara Atito, Muhammad AwaisSelf-Supervised Kullback-Leibler Divergence
fg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculum
May 12, 2026Mingxiong Lin, Zhangquan Gong, Maowen Tang +6Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
May 11, 2026Siqi Zhu, Xuyan Ye, Hongyu Lu +2On-Policy Distillation Teacher
Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning
May 11, 2026Virgile Dine, Teddy FuronSeveral Approximate Unlearning Strategies Exact Unlearning
A Spectral Framework for Closed-Form Relative Density Estimation
May 11, 2026Francis BachDensity Ratio Estimation Bregman Divergences
BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization
May 11, 2026Venugopalan IyengarQuantization Large Language Model Decoder
Identified-Set Geometry of Distributional Model Extraction under Top- $K$ Censored API Access
May 11, 2026Wenhua Nie, ZiCheng Zhu, Jianan Wu +3Kullback-Leibler Divergence Top-K
TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
May 11, 2026Jiaxuan Wang, Xuan Ouyang, Zhiyu Chen +4Unsupervised On-Policy Self-Distillation On-Policy Distillation
Differentially Private Sampling from Distributions via Wasserstein Projection
May 11, 2026Shokichi Takakura, Seng Pei Liew, Satoshi HasegawaDifferential Privacy Wasserstein Distance
expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling
May 11, 2026Mingxiong Lin, Zhangquan Gong, Maowen Tang +6Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
May 10, 2026Haoyang Zhou, Li Kong, Shijie Ren +4Diffusion Language Models Kullback-Leibler Divergence
Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
May 9, 2026Le-Tuyet-Nhi Pham, Giovanni Conforti, Zhenjie Ren +1Conditional Flow Matching Maximum Mean Discrepancy
KL for a KL: On-Policy Distillation with Control Variate Baseline
May 8, 2026Minjae Oh, Sangjun Song, Gyubin Choi +2On-Policy Distillation Kullback-Leibler Divergence
Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization
May 7, 2026Ruotong Sun, Ermin WeiSpectral Preconditioning Orthogonality
Information Theoretic Adversarial Training of Large Language Models
May 6, 2026Yiwei Zhang, Jeremiah Birrell, Reza Ebrahimi +3Language Model Evasion Attacks Adversarial Transferability
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
May 6, 2026Xin Yu, Liuchen Liao, Yiwen Zhang +3Unsupervised On-Policy Self-Distillation On-Policy Distillation
DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment
May 5, 2026Hongbo Jin, Rongpeng Zhu, Zhongjing Du +4Multi-Objective Policy Optimization Credit Assignment
Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-Tuning
May 4, 2026Mehryar Mohri, Jon Schneider, Yutao ZhongKullback-Leibler Divergence Training-Inference Mismatch
Binary Rewards and Reinforcement Learning: Fundamental Challenges
May 4, 2026Marc DymetmanReinforcement Learning With Verifiable Reward Kullback-Leibler Divergence
Exponential families from a single KL identity
Apr 30, 2026Marc DymetmanKullback-Leibler Divergence Exponents
Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant
Apr 27, 2026Paolo D'AlbertoKey-Value Cache Quantization Rate-Distortion Theory
Scaling Properties of Continuous Diffusion Spoken Language Models
Apr 27, 2026Jason Ramapuram, Eeshan Gunesh Dhekane, Amitis Shidani +6Diffusion Language Models Scaling Laws
TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
Apr 27, 2026Jiaqi Wang, Wenhao Zhang, Weijie Shi +2On-Policy Distillation Curriculum
Even More Guarantees for Variational Inference in the Presence of Symmetries
Apr 23, 2026Lena Zellinger, Antonio VergariVariational Inference Variational
Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference
Apr 22, 2026Chao Wang, Luca Nepote, Giulio Franzese +1Single-Cell Rna Sequencing Kullback-Leibler Divergence
Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales
Apr 22, 2026Samuel SalfatiImportance Kullback-Leibler Divergence
Properties and limitations of geometric tempering for gradient flow dynamics
Apr 22, 2026Francesca Romana Crucinio, Sahani PathirajaWasserstein Gradient Flows Fisher Information
Logit Distance Bounds Representational Similarity
Feb 17, 2026Beatrix M. G. Nielsen, Emanuele Marconato, Luigi Gresele +2Kullback-Leibler Divergence Logit Lens
Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
Feb 16, 2026Daniil Dmitriev, Zhihan Huang, Yuting WeiScore-Based Diffusion Model Discrete Diffusion Model
A Gaussian Perspective for Distributional Discrepancy in Generative Diffusion Models
Jan 20, 2026Qiang Sun, H. Vincent Poor, Wenyi ZhangKullback-Leibler Divergence 3D Gaussian Splatting
From Zipf's Law to Neural Scaling through Heaps' Law and Hilberg's Hypothesis
Dec 15, 2025Łukasz DębowskiPower-Law Distribution Kullback-Leibler Divergence
Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization
Sep 3, 2025Wu Lin, Scott C. Lowe, Felix Dangel +3Neural Network Optimization Kullback-Leibler Divergence
GeLaCo: An Evolutionary Approach to Layer Compression
Jul 14, 2025David Ponce, Thierry Etchegoyhen, Javier Del SerLarge Language Model Compression Context Compression
Spherical Cauchy Variational Autoencoders: Heavy Angular Tails and Exact KL Evaluation
Jun 26, 2025Lukas Sablica, Kurt HornikPosterior Kullback-Leibler Divergence
The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis
Jun 13, 2025Bernardo P. Schaeffer, Ricardo M. S. Rosa, Glauco ValleScore-Based Diffusion Model Stochastic Differential Equations
A Jump-Diffusion Framework for Irregular Time Series Generation
May 29, 2025O. Pfohl, J. Chemseddine, P. Hagemann +3Synthetic Time Series Stochastic Systems
Inclusive KL Gradient Flows: Otto-Wasserstein, Fisher-Rao-Gaussian, and Local-Estimator Dynamics
Oct 31, 2024Jia-Jie ZhuWasserstein Gradient Flows Variational Inference
REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent
Date pendingQian Zhang, Yaoming Li, Zhewen Tan +9Large Language Model Quantization Weight-Only Quantization

May 14, 2026 · cs.LGJ/K move · Enter open · S save

Fast Rates for Inverse Reinforcement Learning

Andreas Schlaginhaufen, Maryam Kamgarpour

Sycamore, EPFL

We establish novel structural and statistical results for entropy-regularized min-max inverse reinforcement learning (Min-Max-IRL) with linear reward classes in finite-horizon MDPs with Borel state and action spaces. On the structural side, we show that maximum likelihood estimation (MLE) and Min-Max-IRL are equivalent at the population level, and at the empirical level under deterministic dynamics. On the statistical side, exploiting pseudo-self-concordance of the Min-Max-IRL loss, we prove that both the trajectory-level KL divergence and the squared parameter error in the Hessian norm decay at the fast rate

\mathcal{O}(n^{-1})

, where

n

is the number of expert trajectories. Our guarantees apply under misspecification and require no exploration assumptions. We further extend reward-identifiability results to general Borel spaces and derive novel results on the derivatives of the soft-optimal value function with respect to reward parameters.

Entropy Regularized Reinforcement Learning Kullback-Leibler Divergence

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

1 new paper

7 new papers

1 new paper

Latest in Kullback-Leibler Divergence