Develops possibilistic VI using maxitive Donsker-Varadhan formulation.
problem Adapting VI to possibilistic framework to handle uncertainty.
method Maxitive Donsker-Varadhan formulation for possibilistic VI.
result CBOpt optimizers achieve competitive performance in image classification.
Unified framework for anytime-valid PAC-Bayes bounds.
problem Deriving time-uniform PAC-Bayes bounds for stochastic processes.
method Combines four tools: nonnegative supermartingales, method of mixtures, Donsker-Varadhan formula, and Ville's inequality.
result Unified PAC-Bayes theorem for a wide class of discrete stochastic processes.
PA reinterpreted as SB problem, unifying thermodynamics and optimal transport.
problem Optimizing discrete-time paths between probability distributions.
method Schrödinger Bridge theory, solving variational problems.
result PA's reweighting step derived from Schrödinger system.
Optimal tests for composite nulls achieve the KL inf lower bound.
problem Designing optimal tests for composite null hypotheses.
method Constructive schemes based on universal e-processes.
result Optimal tests match the KL inf lower bound as α → 0.
Recently, a method called the Mutual Information Neural Estimator (MINE) that uses neural networks has been proposed to estimate mutual information and more generally the Kullback-Leibler (KL) divergence between two distributions. The method uses the Donsker-Varadhan representation to arrive at the estimate of the KL d…
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.
We consider the problem of robustly maximizing the growth rate of investor wealth in the presence of model uncertainty. Possible models are all those under which the assets' region E and instantaneous covariation c are known, and where additionally the assets are stable in that their occupancy time measures converg…
CFIL uses coupled flows to model state distributions for imitation learning.
problem Lack of explicit modeling of state distributions in reinforcement and imitation learning.
method Coupled normalizing flows for state and state-action distributions.
result CFIL achieves state-of-the-art performance on benchmark tasks.
New variational formula for Rényi divergences improves neural network estimation in high dimensions.
problem Estimating Rényi divergences in high-dimensional systems.
method Derive and apply a variational formula for Rényi divergences over various function spaces.
result Neural network estimators of Rényi divergences are consistent under certain conditions.
New insights link RLHF and contrastive learning for better model alignment.
problem Aligning large language models with human values.
method Interpreting RLHF and DPO as contrastive learning methods based on mutual information.
result Proposed Mutual Information Optimization (MIO) improves model performance.
Misspecification-Aware Simulation-Based Inference via Side-Channel Guidance
problem Simulation-based inference (SBI) of latent parameters is hindered by simulator misspecification.
method Misspecification-Aware Simulation-Based Inference (MA-SBI) turns side-channel text into a posterior correction.
result MA-SBI matches the oracle posterior across 10 seeds and two backbones.
A single algebraic identity unifies information-theoretic variational results.
problem Deriving and generalizing classical information-theoretic variational results
method Proving a single algebraic mixed coincidence identity
result Unified derivation of classical cornerstones of information theory