Amortized Conditional Normalized Maximum Likelihood
While deep neural networks provide good performance for a range of challenging tasks, calibration and uncertainty estimation remain major challenges. In this paper, we propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation, calibration, and out-of-distribution robustness with deep networks. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle, but is computationally intractable to evaluate exactly for all but the simplest of model classes. We propose to use approximate Bayesian inference technqiues to produce a tractable approximation to the CNML distribution. Our approach can be combined with any approximate inference algorithm that provides tractable posterior densities over model parameters. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of and calibration on out-of-distribution inputs.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceSimilar Papers 제목 키워드 기반
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation
While deep neural networks provide good performance for a range of challenging tasks, calibration and uncertainty estimation remain major challenges, especially under distribution shift. In this paper, we propose the amo…
Bayesian InferenceMaximum Likelihood Learning of Unnormalized Models for Simulation-Based Inference
We introduce two synthetic likelihood methods for Simulation-Based Inference (SBI), to conduct either amortized or targeted inference from experimental observations when a high-fidelity simulator is available. Both metho…
Reinforcement Learning with Bayesian Classifiers: Efficient Skill Learning from Outcome Examples
Exploration in reinforcement learning is, in general, a challenging problem. In this work, we study a more tractable class of reinforcement learning problems defined by data that provides examples of successful outcome s…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Bayesian Properties of Normalized Maximum Likelihood and its Fast Computation
The normalized maximized likelihood (NML) provides the minimax regret solution in universal data compression, gambling, and prediction, and it plays an essential role in the minimum description length (MDL) method of sta…
Data CompressionPredictionLearning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler
Due to the intractable partition function, training energy-based models (EBMs) by maximum likelihood requires Markov chain Monte Carlo (MCMC) sampling to approximate the gradient of the Kullback-Leibler divergence betwee…