Two entropy measures quantify suboptimal portfolio performance.
problem Measuring suboptimality in investment portfolios.
method Relative entropy (KL divergence) calculations.
result Suboptimal portfolios appear better than Kelly portfolios under certain measures.
This paper provides efficient algorithms for computing entropy and KL divergence in Bayesian networks.
problem Computing entropy and KL divergence for Bayesian networks efficiently.
method Leveraging the graphical structure of Bayesian networks, the paper provides computationally efficient algorithms.
result Reduces computational complexity of KL divergence from cubic to quadratic for Gaussian BNs.
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.
Paper characterizes optimal language model alignment methods.
problem Aligning language models to maximize reward while keeping them close to the original model.
method KL-constrained reinforcement learning and best-of-N methods.
result Optimal KL-constrained RL solution has a large deviation principle rate function.
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.
A new classifier method detects out-of-distribution samples by minimizing KL divergence.
problem Detecting out-of-distribution samples in neural networks.
method Training a confident-classifier by minimizing KL divergence and maximizing entropy, or adding a reject class.
result The confident-classifier still yields high confidence for OOD samples far from the in-distribution.
Estimating entropy and mutual information consistently is important for many machine learning applications. The Kozachenko-Leonenko (KL) estimator (Kozachenko & Leonenko, 1987) is a widely used nonparametric estimator for the entropy of multivariate continuous random variables, as well as the basis of the mutual inform…
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 ε -optimal policies. We define On-Average KL-Privacy and present its properties and connections to differential privacy, generalization and information-theoretic quantities including max-information and mutual information. The new definition significantly weakens differential privacy, while preserving its minimalistic design features such …
Paper analyzes KSG mutual information estimator for smooth distributions.
problem Analyzing the convergence rate of KSG estimator for smooth distributions.
method Adaptive recombination of KL entropy estimators analysis.
result Convergence rate of KSG estimator for smooth distributions is analyzed.
There has been a growing interest in mutual information measures due to their wide range of applications in Machine Learning and Computer Vision. In this paper, we present a generalized structured regression framework based on Shama-Mittal divergence, a relative entropy measure, which is introduced to the Machine Learn…
New analysis shows entropy term cancels out in likelihood-based OOD detection.
problem Curious likelihood values for out-of-distribution data.
method Decomposed average likelihood into KL divergence and entropy terms.
result Entropy term explains OOD behaviour and cancels out in expectation.
Improved language models using ratio-matching and KL divergence.
problem Efficiently modeling discrete data with diffusion models.
method Introduced new theorems and a novel CTMC transition-rate matrix for ratio-matching and KL divergence.
result 10-15% improvement in perplexity and faster training steps.
We present a derivation of the Kullback Leibler (KL)-Divergence (also known as Relative Entropy) for the von Mises Fisher (VMF) Distribution in d d d -dimensions.
Paper proposes SL to improve DNN learning with noisy labels.
problem Learning with noisy labels in deep neural networks.
method Symmetric Cross Entropy (SL) with Reverse Cross Entropy (RCE).
result SL outperforms state-of-the-art methods on various datasets.
New bounds close the score matching gap for diffusion models.
problem The difference between sample quality and score matching loss in diffusion models.
method Theoretical analysis of score matching gap, developing tighter bounds for KL divergence, reverse KL divergence, and Wasserstein distance.
result The quality of score approximation impacts closing the score matching gap for low noise scales.
Entropy regularization improves policy optimization in reinforcement learning.
problem Improving policy optimization in reinforcement learning.
method Entropy regularization is introduced to soften the greedy policy towards a more diverse softmax policy, leading to a continuously parameterized algorithm that interpolates between policy gradient and Q-learning.
result An intermediate algorithm can improve performance in reinforcement learning.
Paper improves MIRACLE for faster, more robust neural network compression.
problem Efficiently compressing neural networks while maintaining performance.
method Introduces Mean-KL parameterization to constrain compression cost.
result Mean-KL parameterization leads to twice as fast convergence and more robust compression.
Entropy-based decoding improves DLM sampling efficiency.
problem Decoding strategy challenges in flexible DLMs.
method Entropy sum-based confidence-based decoding.
result Entropy sum-based decoding achieves ε \varepsilon ε -accuracy with O ~ ( H ( X 0 ) / ε ) \widetilde O(H(X_0)/\varepsilon) O ( H ( X 0 ) / ε ) iterations. 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 T T T that scales inversely with KL regularization strength β β β . Two new metrics assess LLM faithfulness and entropy, improving model reliability.
problem Evaluating the accuracy of LLMs in generating coherent responses.
method Proposes SF and SEP metrics based on information theory and thermodynamics.
result High SF and SEP scores indicate more faithful LLM responses.
AES uses α-divergence to select informative points for BO, improving optimization performance.
problem Optimizing complex functions with limited evaluations.
method AES uses α-divergence to select points based on dependency with global maximum.
result AES outperforms other information-based acquisition functions in various experiments.
New method controls classifier guidance in diffusion models.
problem Improving classifier guidance in diffusion models.
method Cross-entropy control of classifier gradients.
result Effective guidance vectors with mean squared error O ( d ε ) O(d \varepsilon ) O ( d ε ) . 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.
MAXENT method outperforms ML in sparse data with specific prior correlations.
problem Evaluating MAXENT method's validity limits and comparing it with ML.
method Bayesian decision theory, Dirichlet density, KL distance, regularized maximum likelihood.
result MAXENT can outperform ML in sparse data with specific prior correlations.
The paper explores how information geometry impacts classical CR inequalities.
problem Deriving and generalizing CR inequalities using information geometry.
method Examining Eguchi's theory and applying Amari-Nagoaka's theory to KL-divergence, and then extending to other divergences.
result Generalized CR inequalities derived from various divergences.
We analyze the Kozachenko--Leonenko (KL) nearest neighbor estimator for the differential entropy. We obtain the first uniform upper bound on its performance over Hölder balls on a torus without assuming any conditions on how close the density could be from zero. Accompanying a new minimax lower bound over the Hölder ba…
The ability of many powerful machine learning algorithms to deal with large data sets without compromise is often hampered by computationally expensive linear algebra tasks, of which calculating the log determinant is a canonical example. In this paper we demonstrate the optimality of Maximum Entropy methods in approxi…
Study shows fast rates for inverse reinforcement learning with linear rewards.
problem Entropy-regularized min-max inverse reinforcement learning in finite-horizon MDPs.
method Structural and statistical analysis of Min-Max-IRL with pseudo-self-concordance.
result Both trajectory-level KL divergence and parameter error decay at O ( n − 1 ) \mathcal{O}(n^{-1}) O ( n − 1 ) . Mutual information bounds generalization error in variational classifiers.
problem Controlling overfitting in variational classifiers.
method Derive bounds on generalization error using mutual information.
result Mutual information bounds the generalization error in variational classifiers.
Trust-region methods and natural gradients are equivalent in certain policy search scenarios.
problem Improving policy search methods in continuous control tasks.
method Introducing compatible policy search (COPOS) that uses natural parameterization and compatible value function approximation to control entropy loss.
result COPOS yields state-of-the-art results in challenging tasks and reduces entropy loss.
Paper revisits FRAME model, explaining instability and proposing a new metric.
problem Unstable training energy in FRAME model.
method Theoretical analysis using particle physics, proposing a new Wasserstein distance.
result Proposed Wasserstein distance stabilizes energy dissipation and maintains statistical consistency.
FORE evaluates occupancy ratios without requiring Bellman completeness.
problem Offline reinforcement learning occupancy ratio estimation.
method Fitted occupancy-ratio evaluation (FORE) using adjoint Bellman recursion.
result FORE achieves convergence in KL without Bellman completeness.
Unified framework for analyzing gradient flows of measures with exponential decay of entropy.
problem Analyzing exponential decay of entropy functionals in gradient flows of measures.
method Characterization of global exponential decay behaviors using Hellinger-Kantorovich geometry, shape-mass decomposition, and Polyak-Łojasiewicz-type inequalities.
result Unified theoretical framework for gradient flows with complete analysis of exponential decay behaviors.
This paper improves Bayesian inference for predictive models with limited data.
problem Effective uncertainty quantification for training predictive models with limited data.
method Entropy-regularized gradient estimators to approximate the Bayesian posterior.
result The method generates diverse samples from the posterior distribution efficiently.
This work extends ME-RL using diffusion models to sample optimal policies.
problem Sampling from the optimal policy trajectory distribution in ME-RL.
method Introducing Diffusion-Augmented Markov Decision Processes (DA-MDPs) to minimize reverse KL divergence.
result DA-MDPs enable seamless integration into various ME-RL methods and outperform baselines.
This study analyzes theoretical guarantees for VI with fixed-variance Gaussian mixtures.
problem Theoretical analysis of variational inference with non-Gaussian distributions.
method Formulates variational inference as minimizing a mollified relative entropy, solving it through gradient descent on particle positions.
result Establishes descent lemma and approximation error bounds for optimization of variational inference.
NLE embeds labels for domain adaptation with neural networks.
problem Adapting deep neural networks with unpaired source and target domain data.
method Distill source-domain knowledge into l-vectors, soft targets for adaptation.
result 14.1% relative word error rate reduction over direct re-training.
Improved sampling from complex distributions with reduced bias.
problem Reducing bias in high-dimensional sampling algorithms.
method Hierarchical entropy analysis to weaken assumptions and expand scope.
result Bias reduction in low-dimensional marginals scales with lower dimension, not full dimension.
EGFs use ergodicity to simplify generative flows for easier training and imitation learning.
problem Challenges in training generative flows, especially in continuous settings and for imitation learning.
method EGFs leverage ergodicity to build simple flows with universality guarantees and tractable FM loss. They introduce a KL-weakFM loss for IL training without a separate reward model.
result EGFs simplify generative flow training and enable effective imitation learning.
Study quantifies model risk in dynamic portfolio selection using KL divergence.
problem Model risk in financial portfolio selection under uncertainty.
method Defined model risk as KL divergence loss, solved nonlinear equations for optimal robust strategy.
result Optimal robust strategy can be obtained semi-analytically in worst case scenario.
Unified framework for distribution shift estimation, explanation, and improvement.
problem Estimating, explaining, and improving model performance on target domains with distribution shift.
method Entropic Projection Alignment (EPA) aligns source and target distributions by matching moments and minimizing KL divergence.
result EPA consistently outperforms state-of-the-art baselines while offering computational efficiency.
A discrete diffusion model learns denoising, scoring, and bridging in different coordinates.
problem Understanding what a discrete diffusion model learns in different coordinate systems.
method Rigorous derivation of continuous-time Markov chain ELBO, Oracle Distance theorem, and exact coordinates for optimizer.
result The negative ELBO is exactly equal to the data entropy plus the path KL from the oracle reverse process to the learned one.
Paper presents a bias mitigation method using maximum entropy.
problem Bias in datasets due to over/under-representation of groups.
method Maximum entropy principle applied to data preprocessing.
result Achieves target fairness metrics and maintains classifier accuracy.
Paper introduces SDM for detecting LLM hallucinations, improving on entropy tests.
problem Challenges of Large Language Models (LLMs) with non-factual, nonsensical responses.
method Joint clustering on sentence embeddings to measure semantic divergence between prompts and responses.
result SDM framework detects deeper form of arbitrariness in LLM responses.
This study proposes hidden state curiosity to enhance RL models' resilience against noise.
problem Curiosity traps in RL models distract agents from discovering novel experiences.
method Proposed hidden state curiosity based on the Free Energy Principle to reward agents for KL divergence between predictive priors and posteriors.
result Agents with hidden state curiosity are more resilient against curiosity traps compared to those with prediction error curiosity.
New loss functions based on f-divergences improve language model performance.
problem Improving multiclass classification and language modeling performance.
method Constructing new convex loss functions using f-divergences and deriving an operator for computation.
result The α α α -divergence loss function with α = 1.5 α=1.5 α = 1.5 performs well across various tasks. New method improves sampling for weakly log-concave posteriors.
problem Sampling from weakly log-concave posterior distributions.
method Stochastic Langevin Monte Carlo with over-damped diffusion.
result Simulation horizon is ( d log ( n ) 2 ) ( 1 + r ) 2 (d \log(n)^2)^{(1+r)^2} ( d log ( n ) 2 ) ( 1 + r ) 2 with Poisson subsampling.