The paper proposes a new method to measure risk with fine-grained tail sensitivity.
problem Risk measures that do not account for tail sensitivity are insufficient for machine learning systems.
method The approach involves specifying a reference distribution with desired tail behavior and constructing risk measures compatible with this upper probability.
result Risk measures with fine-grained tail sensitivity can replace the expectation operator in machine learning systems.
New optimization method corrects data-driven optimizer's curse.
problem Over-optimistic evaluation in data-driven optimization.
method Smoothed f-Divergence Distributionally Robust Optimization (DRO). result Statistical bound on out-of-sample performance nearly tightest.
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…
Framework for quantifying uncertainty in dynamic processes.
problem Quantifying uncertainty in dynamic stochastic processes.
method Define dynamic uncertainty sets and dynamic robust risk measures.
result Dynamic robust risk measures are time-consistent under specific uncertainty sets.
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-divergence loss function with α=1.5 performs well across various tasks. Technical report on f-divergences and f-GAN training properties.
problem Understanding and optimizing f-divergences for GAN training.
method Elementary derivation and detailed expressions of f-divergences and their variational lower bounds.
result Informative properties of f-divergences and f-GAN training, including gradient matching and stability improvements.
The paper improves model robustness by regularizing posterior differences.
problem Improving model robustness in noisy input scenarios.
method Posterior differential regularization with f-divergence. result Regularizing with f-divergence improves model robustness. New bounds for Neyman-Pearson region using f-divergences.
problem Bounding the Neyman-Pearson region for hypothesis testing.
method Establishing novel lower and upper bounds using f-divergences. result Best possible lower bound for the Neyman-Pearson boundary using hockey-stick f-divergences. New method improves imitation learning from expert observations.
problem Challenges in imitation learning from observation setting.
method Reparameterized Variational Divergence Minimization.
result Our method outperforms baseline approaches in low-dimensional tasks.
Regularizes f-divergences with MMD to analyze Wasserstein flows.
problem Limitations of f-divergences in measures' support. method Rewriting MMD regularization as Moreau envelope in RKHS, analyzing gradients.
result Analysis of Wasserstein flows of MMD-regularized f-divergences. 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. Paper introduces f-divergence variational inference for broader application.
problem Variational inference limited to specific divergences.
method Generalizes variational inference to all f-divergences using f-divergence minimization.
result Unified framework for variational inference with arbitrary f-divergences.
New f-divergence measures improve robustness in noisy label learning.
problem Improving robustness in learning with noisy labels.
method Derived decoupling property of f-divergence measures under label noise. result Properly defined f-divergence measures are robust with label noise. Proposes practical kernel tests for f-divergences with theoretical guarantees.
problem Two-sample testing and machine unlearning evaluation.
method Regularized f-divergence kernel tests, adaptive to hyperparameters. result Different f-divergences highlight localized differences. f-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics and information theory such as Kullback-Leibler divergence, chi-squared divergence, squared Hellinger distance, total variation distance e…
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.
Paper proposes f-EBM for training deep EBMs using various f-divergences.
problem Training deep EBMs with intractable partition functions.
method Introduces f-EBM framework and optimization algorithm for any f-divergence.
result f-EBM outperforms contrastive divergence and other f-divergences.
Improves DRO with Bayesian Ambiguity Sets for model misspecification.
problem Overly conservative decisions due to misspecified models in DRO.
method Introduces DRO-RoBAS with robust posterior predictive distribution.
result Outperforms other Bayesian and empirical DRO approaches in out-of-sample performance.
Rank-statistic method approximates f-divergences without density-ratio estimation.
problem Approximating f-divergences without explicit density-ratio estimation. method Mapping distribution rank histograms to discrete f-divergence and averaging over random projections. result The rank-statistic estimator is a lower bound of the true f-divergence and converges under mild conditions. Optimal policies in Markov decision processes (MDPs) are very sensitive to model misspecification. This raises serious concerns about deploying them in high-stake domains. Robust MDPs (RMDP) provide a promising framework to mitigate vulnerabilities by computing policies with worst-case guarantees in reinforcement learn…
Optimal transport with f-divergence regularization using generalized Sinkhorn algorithm.
problem Optimal transport with f-divergence regularization. method Generalized Sinkhorn algorithm for solving optimal transport problems with various f-divergences. result Strong duality holds, optimums are attained, and convergence to an optimal solution is guaranteed under certain conditions.
We introduce a new approximation of f-divergences for machine learning.
problem Variational representations of f-divergences for machine learning. method Definition and analysis of Moreau-Yosida approximation of f-divergences with the Wasserstein-1 metric. result Generalization and relaxation of hard Lipschitz constraints in f-divergences. The paper analyzes the statistical properties of GANs using f-divergence.
problem Understanding the statistical behavior of GANs and comparing different f-divergences. method Asymptotic analysis of f-divergence GANs, including Kullback-Leibler divergence. result Asymptotically equivalent GANs with the same discriminator classes for correctly specified models.
This work develops a unified framework for RLHF with general f-divergence regularization.
problem Theoretical understanding of general f-divergence regularization in RLHF. method Holistic approach across f-divergence class, two algorithms based on distinct sampling principles. result Provably efficient algorithms with O(logT) regret and O(1/T) sub-optimality gap. Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. E…
This paper compares different DRO formulations for pension fund management.
problem Navigating uncertainty in asset liability management for pension funds.
method Three DRO formulations: mixture, box, and Wasserstein ambiguity sets.
result Wasserstein and box ambiguity sets outperform traditional approaches in fund performance.
Understanding and measuring model risk is important to financial practitioners. However, there lacks a non-parametric approach to model risk quantification in a dynamic setting and with path-dependent losses. We propose a complete theory generalizing the relative-entropic approach by Glasserman and Xu to the dynamic ca…
Paper analyzes sample complexity for offline f-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(ε−1) sample complexity. result Achieves ildeO(ε−1) sample complexity for reverse KL divergence, surpassing existing bounds. Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks, alternative non-likelihood training criteria have been proposed. Whilst not necessarily…
New model learns better policies from expert demonstrations with higher efficiency.
problem Learning accurate policies from expert demonstrations with high efficiency.
method Generative adversarial imitation learning (GAIL) model that learns f-divergence automatically. result Learns better policies with higher data efficiency in physics-based control tasks.
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.
A density ratio is defined by the ratio of two probability densities. We study the inference problem of density ratios and apply a semi-parametric density-ratio estimator to the two-sample homogeneity test. In the proposed test procedure, the f-divergence between two probability densities is estimated using a density-r…
Paper investigates Lambda Value-at-Risk under ambiguity and risk sharing.
problem Investigates Lambda Value-at-Risk under ambiguity and risk sharing.
method Establishes equivalence of robust ΛVaR and traditional ΛVaR under ambiguity sets, analyzes properties, derives explicit formulas, and explores risk sharing. result Unified and extended the concept of Value-at-Risk under ambiguity, derived explicit formulas for specific ambiguity sets, and explored risk sharing.
Adapts AUM to identify ambiguous tasks in crowdsourced learning, improving generalization.
problem Discerning ambiguous tasks in crowdsourced labels to prevent mislabeling.
method Introduces Weighted Areas Under the Margin (WAUM) to average AUMs weighted by task-specific scores.
result Improves generalization performance by discarding ambiguous tasks.
We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter representation to derive a general f-divergence estimator based on t…
Unified framework for generative models incorporating VAE and GAN.
problem Flexible incorporation of diverse measures of probability distance in generative models.
method Unified f-divergence generative model (f-GM) that incorporates both VAE and f-GAN.
result Unified f-GM enables flexible design of f-divergence functions without changing network structure.
New f-Betas for portfolio optimization using f-divergence risk measures.
problem Optimizing portfolio performance under varying market conditions.
method Derive f-Betas and Hellinger-Betas, using f-divergence risk measures.
result Demonstrated new Beta metrics provide better performance under stress.
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.
CADRO optimizes DRO by reducing conservatism through cost-aware ambiguity sets.
problem Optimizing solutions under uncertainty with reduced conservatism.
method CADRO uses a cost-aware ambiguity set to reduce DRO's conservatism.
result CADRO provides high-confidence upper bounds and consistent estimators of out-of-sample expected cost.
Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is det…
Improves Bridge estimators using f-GAN to minimize RMSE.
problem Estimating ratios of normalizing constants efficiently.
method Proposes f-GAN-Bridge estimator using bijective transformations and f-divergence minimization.
result Optimal in minimizing asymptotic RMSE among candidate transformations.
Proposes a method to learn adaptive ambiguity sets for robust optimization.
problem Misspecification in distributionally robust optimization (DRO).
method Learned predictive ambiguity sets (LPAS) using deep contextual models.
result Significantly improves portfolio optimization performance compared to baselines.
The paper uses EVT to improve tail risk measures under ambiguity sets.
problem Misspecification of tail risk measures leads to inflated risk estimates.
method Applies Extreme Value Theory to derive worst-case tail risk under ambiguity sets.
result Proposes a tail-calibrated ambiguity design that preserves nominal tail asymptotic scaling.
Improved UDA framework using f-divergence measures.
problem Addressing distribution shifts in machine learning.
method Refined f-divergence-based discrepancy and f-domain discrepancy. result Novel target error and sample complexity bounds.
According to conventional wisdom, ambiguity accelerates optimal timing by decreasing the value of waiting in comparison with the unambiguous benchmark case. We study this mechanism in a multidimensional setting and show that in a multifactor model ambiguity does not only influence the rate at which the underlying proce…
Model cash management under ambiguity using maxmin preferences and diffusion.
problem Optimizing cash reserves in the presence of ambiguity.
method Singular control model with maxmin preferences, verified using Dynkin games.
result Higher expected costs and narrower inaction region under increased ambiguity.
The t-distributed Stochastic Neighbor Embedding (t-SNE) is a powerful and popular method for visualizing high-dimensional data. It minimizes the Kullback-Leibler (KL) divergence between the original and embedded data distributions. In this work, we propose extending this method to other f-divergences. We analytically a…
New method estimates velocity fields for minimizing f-divergences without overfitting.
problem Minimizing statistical discrepancies between target and particle distributions.
method Directly estimate velocity fields using interpolation techniques, proving consistency under mild conditions.
result Consistent estimators of velocity fields improve accuracy in applications like domain adaptation and missing data imputation.