Paper offers a fast convergence theory for offline decision making.
problem Offline decision making problems, including reinforcement learning and off-policy evaluation.
method Introduces a framework (DMOF) and algorithm (EDD) with a fast convergence guarantee.
result Demonstrates a fast convergence guarantee with a lower bound complement.
EDD uses entropy of distance distributions to cluster unlabeled data.
problem Challenges in clustering unlabeled high-dimensional data.
method EDD employs Shannon entropy to quantify distance distribution peaks.
result EDD detects varying degrees of clustering sensitivity.
We extend CS divergence to conditional distributions and show its advantages in time series data and sequential decision making.
problem Quantifying the closeness between conditional distributions.
method Developed and estimated a conditional Cauchy-Schwarz divergence using kernel density estimation.
result Conditional CS divergence outperforms previous methods in time series clustering and sequential decision making.
Disagreement between two classifiers regarding the class membership of an observation in pattern recognition can be indicative of an anomaly and its nuance. As in general classifiers base their decision on class aposteriori probabilities, the most natural approach to detecting classifier incongruence is to use divergen…
A new approach to model rejection using density ratios.
problem Improving model performance through selective prediction.
method Optimization of a loss's risk with φ-divergence regularization to find an idealized data distribution.
result Model rejection can be made by comparing the density ratio of the idealized distribution to the actual data distribution.
The paper improves semi-supervised learning using f-divergences and α-Rényi divergences.
problem Improving semi-supervised learning with noisy pseudo-labels.
method Inspired by f-divergences and α-Rényi divergences, the paper develops new empirical risk functions and regularization techniques. result The new methods show better performance than traditional self-training methods, especially in noisy pseudo-label scenarios.
Efficiently computes indices for UCB and DMED algorithms in reinforcement learning.
problem Efficiently compute indices for UCB and DMED algorithms in reinforcement learning.
method Developed efficient methods to compute indices for UCB and DMED algorithms by solving systems of equations.
result Significant computational time savings and improved regret performance demonstrated.
ERM with f-divergence regularization yields unique solution.
problem Optimizing empirical risk with f-divergence. method Mild conditions on f lead to unique optimal measure. result Equivalence of ERM-fDR to different f-divergence regularization. This paper presents a distance-based discriminative framework for learning with probability distributions. Instead of using kernel mean embeddings or generalized radial basis kernels, we introduce embeddings based on dissimilarity of distributions to some reference distributions denoted as templates. Our framework exte…
We develop a mixture procedure for multi-sensor systems to monitor data streams for a change-point that causes a gradual degradation to a subset of the streams. Observations are assumed to be initially normal random variables with known constant means and variances. After the change-point, observations in the subset wi…
New measures generalize existing ones, linking information and risk.
problem Linking information measures and risk in statistical decision problems.
method Introducing new families of divergence measures and deriving an information processing equality.
result Extension of variational φ-divergence representation to multiple distributions. In this paper we consider the basic version of Reinforcement Learning (RL) that involves computing optimal data driven (adaptive) policies for Markovian decision process with unknown transition probabilities. We provide a brief survey of the state of the art of the area and we compare the performance of the classic UCB…
New algorithm optimizes unimodal bandits using empirical divergence.
problem Optimizing decisions in multi-armed bandit problems with unimodal distributions.
method Indexed Minimum Empirical Divergence (IMED) adapted for unimodal structure.
result IMED-UB algorithm optimally exploits unimodal structure.
Proposes an active RBI framework using Rényi information measures for more informed decision-making.
problem Optimal latent variable estimates in real-time settings with streaming noisy observations.
method Unified inference and query selection steps through Rényi entropy and α-divergence; new objective called Momentum for exploration.
result Analytically demonstrates superior performance compared to conventional methods like mutual information.
Paper presents ERM with f-divergence regularization and its properties.
problem Minimizing empirical risk with f-divergence constraints. method Introduces normalization function and solves ERM-fDR via ODE. result Characterizes difference between empirical risks and provides numerical algorithm.
The paper evaluates biased methods for alpha-divergence minimization.
problem The impact of bias on solutions found for alpha-divergence minimization.
method Empirical evaluation of biased methods for alpha-divergence minimization, focusing on bias effects and dimensionality.
result Solutions are biased towards KL-divergence minimizers and require impractical computation in high dimensions to minimize alpha-divergence.
Develops a statistical test for IV, improving feature selection reliability.
problem Lack of statistical justification in conventional IV-based feature selection.
method Establishes connection with Jeffreys divergence and proposes a nonparametric hypothesis test.
result The J-Divergence test provides rigorous guarantees and is more reliable than traditional IV thresholds.
Neural networks estimate statistical divergences with performance guarantees.
problem Estimating statistical divergences with theoretical performance guarantees.
method Parametrizing empirical variational form by a neural network and optimizing over parameter space.
result Established non-asymptotic absolute error bounds for neural estimators of four f-divergences. New approach mitigates feedback divergence in imitation learning.
problem Divergence between held-out error and learner performance in imitation learning.
method Identifies covariate shift as the root cause and proposes a simulator-based solution.
result Naive behavioral cloning performs well in real-world decision making problems.
New framework using Jensen-Shannon divergence improves domain adaptation theory.
problem Incoherence between empirical domain adversarial training and theoretical H-divergence. method Established new theoretical framework based on Jensen-Shannon divergence, derived bi-directional upper bounds.
result Framework exhibits flexibilities for various transfer learning problems.
Unified technique for sequential estimation of convex divergences.
problem Estimating convex divergences between distributions.
method Martingale methods and maximal inequalities for reverse submartingales.
result Valid time-uniform confidence sequences for arbitrary stopping times.
New online GP algorithm offers performance guarantees for streaming data.
problem Training and inference of GPs require all historic data, limiting online decision-making.
method Developed a new theoretical framework based on PAC-Bayes theory, optimizing empirical risk and parameter divergence.
result Offers both a guarantee of generalized performance and good accuracy.
An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an optimal controller via direct interaction with the environment. Such interactive d…
We propose to interpret distribution model risk as sensitivity of expected loss to changes in the risk factor distribution, and to measure the distribution model risk of a portfolio by the maximum expected loss over a set of plausible distributions defined in terms of some divergence from an estimated distribution. The…
A new framework for robust policy learning in MDPs with linear mixture dynamics.
problem Off-dynamics challenge in real-world decision-making problems.
method Linear mixture DRMDP framework, meta algorithm for robust policy learning.
result The new framework provides a more refined representation of uncertainties.
Replacing MSE with f-divergence in diffusion models improves robustness under data contamination.
problem Improving robustness of diffusion models under data contamination.
method Replacing MSE with f-divergence in diffusion models.
result Empirical improvement in performance under data contamination.
Paper introduces a new method for learning Bregman divergence from data.
problem Suboptimal performance of classic distance metrics in deep metric learning.
method Learning empirical Bregman divergence from data using deep learning.
result Empirical Bregman divergence method outperforms other methods on public datasets.
The problem of f-divergence estimation is important in the fields of machine learning, information theory, and statistics. While several nonparametric divergence estimators exist, relatively few have known convergence properties. In particular, even for those estimators whose MSE convergence rates are known, the asympt…
We study the problem of detecting an abrupt change to the signal covariance matrix. In particular, the covariance changes from a "white" identity matrix to an unknown spiked or low-rank matrix. Two sequential change-point detection procedures are presented, based on the largest and the smallest eigenvalues of the sampl…
Unified probabilistic perspective on imitation learning methods using divergence minimization.
problem Understanding and improving imitation learning methods for limited demonstration scenarios.
method Unified probabilistic perspective based on divergence minimization.
result State-marginal matching objective contributes most to IRL's superior performance.
The paper introduces a new risk assessment framework using φ-divergence.
problem Assessing risk and decision-making in uncertain conditions.
method Introduces a novel framework called the φ-Divergence Quadrangle.
result Provides a more nuanced understanding of risk through φ-divergence.
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.
The empirical NTK diverges from the NTK in classification problems during overtraining.
problem The divergence of empirical NTK from NTK in classification problems during overtraining.
method Demonstrated strictly positive definiteness of NTKs for FCNs and ResNets. Proved divergence of neural network parameters during training with cross-entropy loss.
result The empirical NTK does not uniformly converge to the NTK across all times on the training samples as the network width increases.
New method detects changes in high-dimensional data from small samples.
problem Detecting changes in high-dimensional data with limited samples.
method Angular kernel scan framework for detecting marginal distributional shifts.
result Exact population mean factorization and asymptotically distribution-free test.
Proposes a new divergence measure for probability distributions.
problem Challenges in estimating divergences from empirical samples.
method Embeds data into RKHS, computes Jensen-Shannon divergence between covariance operators.
result Establishes RJSD as a lower bound on Jensen-Shannon divergence, enabling variational estimation.
Study optimizes tree-based models for better alignment of predicted scores and actual probabilities.
problem Traditional calibration metrics fail to align predicted scores with actual probabilities when score distributions deviate from the underlying data.
method Optimizes tree-based models (Random Forest, XGBoost) using Kullback-Leibler (KL) divergence to minimize the difference between predicted and true probability distributions.
result Optimized tree-based models yield superior alignment between predicted scores and actual probabilities without significant performance loss.
Dual optimization connects ERM-fDR to normalization function.
problem Empirical risk minimization with f-divergence regularization.
method Dual formulation, Legendre-Fenchel transform, implicit function theorem, nonlinear ODE.
result Computational method to calculate normalization function efficiently.
Study scaling of optimal solutions for reliability constraints in resource provisioning.
problem Achieving high reliability in resource provisioning under stringent requirements.
method Chance-constrained optimization, distributionally robust optimization, f-divergence balls, line search.
result Correct scaling properties of optimal decisions are preserved by using appropriate f-divergence balls, leading to conservative yet near-optimal solutions.
New divergences improve score-based methods for multi-modal distributions.
problem Blindness problem in score-based divergences for multi-modal distributions.
method Proposed a new family of divergences to mitigate blindness.
result Improved performance in density estimation compared to traditional approaches.
New framework identifies worst-case shifts for predictive resource allocation models.
problem Identifying harmful shifts in predictive models for resource allocation.
method Hierarchical model structure and submodular optimization for worst-case loss.
result Empirical evidence shows divergent worst-case shifts identified by different metrics.
A method for eliciting expert beliefs using preferential questions and normalizing flows.
problem Eliciting high-dimensional probability distributions from noisy judgments.
method Normalizing flows based on preferential questions with a novel functional prior.
result The method allows for the inference of arbitrarily flexible densities from preferential judgments.
We study sequential change-point detection procedures based on linear sketches of high-dimensional signal vectors using generalized likelihood ratio (GLR) statistics. The GLR statistics allow for an unknown post-change mean that represents an anomaly or novelty. We consider both fixed and time-varying projections, deri…
This paper provides a non-robust interpretation of the distributionally robust optimization (DRO) problem by relating the distributional uncertainties to the chance probabilities. Our analysis allows a decision-maker to interpret the size of the ambiguity set, which is often lack of business meaning, through the chance…
Paper proposes SinkhornDRL for distributional RL using Sinkhorn divergence and regularized Wasserstein loss.
problem Improving distributional reinforcement learning by minimizing Bellman return distribution differences.
method Introduces SinkhornDRL, a distributional RL algorithm using Sinkhorn divergence and regularized Wasserstein loss.
result SinkhornDRL consistently outperforms or matches existing algorithms on Atari games, especially in multi-dimensional reward settings.
New theory explains GAN's high quality but low diversity.
problem Lack of theoretical justification for non-saturating GAN training.
method Showed non-saturating GAN training approximately minimizes a specific f-divergence.
result Non-saturating GAN training minimizes a particular f-divergence.
New PAC-Bayes bounds derived using Legendre transform and f-divergences.
problem Deriving PAC-Bayes bounds under various assumptions.
method Combining Legendre transform and Fenchel--Young inequality to derive change-of-measure inequalities.
result Extended PAC-Bayesian guarantees under tailored assumptions.
Develops a statistical learning framework for personalized asset allocation.
problem Continuous-action decision-making with a large number of characteristics.
method Discretization approach with generalized penalties for penalized regression.
result Improves financial well-being with individualized optimal asset allocation.
This paper provides performance guarantees for neural estimation of statistical distances.
problem Developing performance guarantees for neural estimation of statistical distances.
method Non-asymptotic error bounds using function approximation theorems and empirical process theory.
result Established a fundamental tradeoff between approximation and estimation errors in neural estimation of statistical distances.