Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

59119178237 · Jun 202019922001200920172026
48 results for KL Regularization

Improved fast rates for decision making with forward-KL regularization in contextual bandits.

problem Improving fast rates for decision making with forward-KL regularization in contextual bandits.
method Streamlined analysis of forward-KL-regularized offline CBs, exploiting the pessimism principle and convex-analytical pipeline.
result First ildeO(ε1) ilde{O}(ε^{-1}) upper bounds in tabular and general function approximation settings.

Paper analyzes sample complexity of offline MABs with KL regularization.

problem Optimizing sample complexity for offline decision-making with KL-regularized metrics.
method Sharp analysis of KL-PCB, providing upper and lower bounds.
result Characterizes sample complexity for offline MABs with KL regularization.

Paper analyzes and improves KL-regularized RL for LLMs with logarithmic regret.

problem Improving efficiency of RL fine-tuning for large language models.
method Optimism-based KL-regularized online contextual bandit algorithm with novel regret analysis.
result Achieves an O(ηlog(NRT)dR)\mathcal{O}\big(η\log (N_{\mathcal R} T)\cdot d_{\mathcal R}\big) logarithmic regret bound.

KL regularization helps RL algorithms by implicitly averaging q-values.

problem Understanding why KL regularization improves RL performance.
method An approximate value iteration scheme, studying KL and entropy regularization.
result Strong performance bound combining linear horizon dependency and averaging effect of estimation errors.

New algorithms achieve logarithmic regret in KL-regularized Markov games.

problem Improving sample efficiency in game-theoretic settings with KL regularization.
method Developed OMG and SOMG algorithms for matrix and Markov games, using best response sampling and superoptimistic bonuses.
result Logarithmic regret in TT that scales inversely with KL regularization strength ββ.

KL-regularized RL from expert demos can lead to slow, unstable learning.

problem Pathological training dynamics in KL-regularized RL from expert demonstrations.
method Empirical analysis and non-parametric behavioral reference policies.
result KL-regularized RL can be significantly improved by using non-parametric behavioral policies.

KL-constrained API shows optimization issues and improved with regularization.

problem Optimization issues in KL-constrained API algorithms.
method Comparison of KL divergence as a constraint vs. regularizer, empirical evaluation.
result KL-constrained API is not guaranteed to converge and incurs linear regret.

Personalized sleep staging achieved with single-night data using KL-divergence regularization.

problem Improving automatic sleep staging accuracy with limited single-night data.
method KL-divergence regularization for transfer learning from a pretrained model to a personalized model.
result Personalized sleep staging accuracy of 79.6% with KL-divergence regularization.

This work improves convergence guarantees for unadjusted HMC in KL and Rényi divergences.

problem Understanding convergence properties of unadjusted HMC in divergences like KL and Rényi.
method One-shot couplings to establish regularization and lift convergence bounds.
result Quantitative control of relative density mismatch and warm-start requirements.

Paper tackles offline RL from mixed datasets with adaptive KL regularizer.

problem Challenges in optimizing RL and BC signals with varying action coverage and multiple action modes.
method Adaptively weighted reverse KL divergence regularizer based on TD3 algorithm.
result Empirically outperforms existing offline RL algorithms in MuJoCo locomotion tasks.

Paper analyzes sample complexity for offline ff-divergence-regularized contextual bandits.

problem Lack of tight analyses for sample complexity in offline reinforcement learning.
method Novel pessimism-based analysis for reverse KL divergence, establishing ildeO(ε1) ilde{O}(ε^{-1}) sample complexity.
result Achieves ildeO(ε1) ilde{O}(ε^{-1}) sample complexity for reverse KL divergence, surpassing existing bounds.

This paper solves the multiple reference model problem in RLHF with exact solutions and sample complexity guarantees.

problem Limitations of single reference models in aligning LLMs with human feedback.
method Integrates multiple reference models into RLHF frameworks, addressing theoretical challenges with exact solutions and sample complexity guarantees.
result First exact solution to the multiple reference model problem in reverse KL-regularized RLHF.

Efficiently addresses federated learning challenges with reduced communication and sample complexity.

problem Heterogeneity in data volumes and distributions at different clients compromises model generalization ability.
method Introduces algorithms for communication-efficient Federated Group Distributionally Robust Optimization (FGDRO).
result Communication complexity reduced to O(1/ε4)O(1/ε^4) for FGDRO-CVaR and O(1/ε3)O(1/ε^3) for FGDRO-KL.

POETS optimizes LLMs by combining policy ensembles and KL regularization.

problem Balancing exploration and exploitation in decision-making and optimization.
method POETS uses policy ensembles and KL regularization to optimize LLMs efficiently.
result POETS achieves state-of-the-art sample efficiency across various domains.

New RLHF framework handles general preference oracles without reward functions.

problem Handling general preference oracles without assuming a reward function.
method Developed a minimax game between two LLMs for RLHF under a general preference oracle, focusing on KL-regularized preference.
result Proposed algorithms for efficient offline and online RLHF learning.

New RL method nearly optimally learns policies with generative models.

problem Finding optimal policies in reinforcement learning with generative models.
method Mirror descent value iteration with KL divergence and entropy regularization.
result The method is nearly minimax-optimal for small ε\varepsilon-optimal policies.

Study compares chi-squared divergence and KL-divergence posteriors for PAC-Bayesian bounds.

problem Investigates optimal posteriors for PAC-Bayesian bounds using chi-squared divergence.
method Analyzes bounds for three distance functions, derives FP equations for computation.
result Chi-squared divergence based posteriors have weaker bounds and worse test errors.

EGMU optimizes portfolios using KL divergence, ensuring positive solutions.

problem Constructing multi-factor target-exposure portfolios efficiently and accurately.
method Convex optimization framework minimizing KL divergence, with explicit solvers.
result Established feasibility and uniqueness of strictly positive solutions under convex-hull conditions.

The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the latent variable given the data point is regularized by the prior of the latent variable using Kullback Leibler (KL) divergence. Although the stan…

2018-09-14abs ↗pdf ↗

New method proves fast regret bounds for online RLHF with generalized preferences.

problem Minimizing max-regret in online RLHF with general preferences and bandit feedback.
method Adopted Generalized Bilinear Preference Model (GBPM) to investigate polylogarithmic regret guarantees.
result Proved polylogarithmic regret bounds for Greedy Sampling and Explore-Then-Commit policies under GBPM.

Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeated structure to speed up and regularize learning. We start from the KL regularized expected reward objective which introduces an additional c…

2019-05-03abs ↗pdf ↗

The paper rethinks the use of exponential averaging in machine learning optimization.

problem The inefficiency of using exponential averaging in optimization algorithms.
method The paper connects EA-CM algorithms to Wake of Quadratic regularized models and proposes new algorithms, KLD-WRM.
result The new algorithms outperform existing methods like K-FAC on MNIST.

A new ParVI framework improves particle-based variational inference methods.

problem Non-trivial kernel design in particle-based variational inference methods.
method Proposes a generalized Wasserstein gradient descent (GWG) framework with broader regularizers.
result Demonstrates strong convergence guarantees and effectiveness on simulated and real data.

This work develops a unified framework for RLHF with general ff-divergence regularization.

problem Theoretical understanding of general ff-divergence regularization in RLHF.
method Holistic approach across ff-divergence class, two algorithms based on distinct sampling principles.
result Provably efficient algorithms with O(logT)O(\log T) regret and O(1/T)O(1/T) sub-optimality gap.

Paper addresses variational inference issues in Bayesian neural networks.

problem Negative infinite ELBO for function-space priors in BNNs.
method Regularized KL divergence for well-defined function-space variational inference.
result Method provides competitive uncertainty estimates for BNNs.

Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.

problem Approximating target distributions in conditional diffusion models.
method Using finite Gaussian mixtures with ReLU-network logits as reverse kernels, reducing the problem to static conditional density approximation.
result The resulting neural reverse-kernel class is dense in conditional KL divergence under exact terminal matching.

CPR adds entropy maximization to improve continual learning methods.

problem Catastrophic forgetting in continual learning.
method Classifier-Projection Regularization (CPR) adds an entropy maximization term to existing regularization methods.
result CPR improves accuracy and plasticity in continual learning methods.

DDO-RM improves reward-based policies by converting reward scores into a target distribution.

problem Improving reward-based policies when the reward function is simpler than the policy.
method Converts reward scores into a target distribution and uses KL-regularized mirror-descent updates.
result DDO-RM outperforms DPO in pair accuracy and mean margin.

Researchers establish bounds for SGMs' KL and Wasserstein divergences under various noise schedules.

problem Estimating the error between target and estimated distributions in SGMs.
method Established upper bounds for KL divergence and Wasserstein distance, incorporating target distribution properties and SGM hyperparameters.
result Optimal noise schedules identified for SGMs, improving generative quality.

Optimizes quantile and semi-adversarial regret with novel root-logarithmic regularizers.

problem Minimizes regret in adversarial and semi-adversarial online learning.
method FTRL with root-logarithmic regularizers for quantile and semi-adversarial settings.
result Achieves minimax optimal regret bounds in both paradigms.