The Principle of Uncertain Maximum Entropy

• URL: http://arxiv.org/abs/2305.09868v4
• Date: Wed, 11 Sep 2024 02:14:18 GMT
• Title: The Principle of Uncertain Maximum Entropy
• Abstract summary: We present a new principle we call uncertain maximum entropy that generalizes the classic principle and provides interpretable solutions. We introduce a convex approximation and expectation-maximization based algorithm for finding solutions to our new principle.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The principle of maximum entropy is a well-established technique for choosing a distribution that matches available information while minimizing bias. It finds broad use across scientific disciplines and in machine learning. However, the principle as defined by is susceptible to noise and error in observations. This forces real-world practitioners to use relaxed versions of the principle in an ad hoc way, negatively impacting interpretation. To address this situation, we present a new principle we call uncertain maximum entropy that generalizes the classic principle and provides interpretable solutions irrespective of the observational methods in use. We introduce a convex approximation and expectation-maximization based algorithm for finding solutions to our new principle. Finally, we contrast this new technique with two simpler generally applicable solutions theoretically and experimentally show our technique provides superior accuracy.

Related papers

• Asymptotic quantification of entanglement with a single copy [8.056359341994941]
  This paper introduces a new way of benchmarking the protocol of entanglement distillation (purification) Instead of measuring its yield, we focus on the best error achievable. We show this solution to be given by the reverse relative entropy of entanglement, a single-letter quantity that can be evaluated using only a single copy of a quantum state.
  arXiv  Detail & Related papers  (2024-08-13T17:57:59Z)
• On Maximum Entropy Linear Feature Inversion [7.1795069620810805]
  We revisit the classical problem of inverting dimension-reducing linear mappings using the maximum entropy criterion. We propose a new unified approach that not only specializes to the existing approaches, but offers solutions to new cases.
  arXiv  Detail & Related papers  (2024-07-19T09:52:18Z)
• A Unified Theory of Stochastic Proximal Point Methods without Smoothness [52.30944052987393]
  Proximal point methods have attracted considerable interest owing to their numerical stability and robustness against imperfect tuning. This paper presents a comprehensive analysis of a broad range of variations of the proximal point method (SPPM)
  arXiv  Detail & Related papers  (2024-05-24T21:09:19Z)
• ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference [69.24516189971929]
  In this paper, we introduce a new type of solution in the longitudinal setting: a closed-form ordinary differential equation (ODE) While we still rely on continuous optimization to learn an ODE, the resulting inference machine is no longer a neural network.
  arXiv  Detail & Related papers  (2024-03-16T02:07:45Z)
• The Principle of Minimum Pressure Gradient: An Alternative Basis for Physics-Informed Learning of Incompressible Fluid Mechanics [0.0]
  The proposed approach uses the principle of minimum pressure gradient combined with the continuity constraint to train a neural network and predict the flow field in incompressible fluids. We show that it reduces the computational time per training epoch when compared to the conventional approach.
  arXiv  Detail & Related papers  (2024-01-15T06:12:22Z)
• Instance-Dependent Generalization Bounds via Optimal Transport [51.71650746285469]
  Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks. We derive instance-dependent generalization bounds that depend on the local Lipschitz regularity of the learned prediction function in the data space. We empirically analyze our generalization bounds for neural networks, showing that the bound values are meaningful and capture the effect of popular regularization methods during training.
  arXiv  Detail & Related papers  (2022-11-02T16:39:42Z)
• A Primal-Dual Approach to Solving Variational Inequalities with General Constraints [54.62996442406718]
  Yang et al. (2023) recently showed how to use first-order gradient methods to solve general variational inequalities. We prove the convergence of this method and show that the gap function of the last iterate of the method decreases at a rate of $O(frac1sqrtK)$ when the operator is $L$-Lipschitz and monotone.
  arXiv  Detail & Related papers  (2022-10-27T17:59:09Z)
• On the Importance of Gradient Norm in PAC-Bayesian Bounds [92.82627080794491]
  We propose a new generalization bound that exploits the contractivity of the log-Sobolev inequalities. We empirically analyze the effect of this new loss-gradient norm term on different neural architectures.
  arXiv  Detail & Related papers  (2022-10-12T12:49:20Z)
• IRL with Partial Observations using the Principle of Uncertain Maximum Entropy [8.296684637620553]
  We introduce the principle of uncertain maximum entropy and present an expectation-maximization based solution. We experimentally demonstrate the improved robustness to noisy data offered by our technique in a maximum causal entropy inverse reinforcement learning domain.
  arXiv  Detail & Related papers  (2022-08-15T03:22:46Z)
• Principled Knowledge Extrapolation with GANs [92.62635018136476]
  We study counterfactual synthesis from a new perspective of knowledge extrapolation. We show that an adversarial game with a closed-form discriminator can be used to address the knowledge extrapolation problem. Our method enjoys both elegant theoretical guarantees and superior performance in many scenarios.
  arXiv  Detail & Related papers  (2022-05-21T08:39:42Z)
• Notes on Generalizing the Maximum Entropy Principle to Uncertain Data [0.0]
  We generalize the principle of maximum entropy for computing a distribution with the least amount of information possible. We show that our technique generalizes the principle of maximum entropy and latent maximum entropy. We discuss a generally applicable regularization technique for adding error terms to feature expectation constraints in the event of limited data.
  arXiv  Detail & Related papers  (2021-09-09T19:43:28Z)
• Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization [77.24152933825238]
  We show that for linear classification tasks we need stronger restrictions on the distribution shifts, or otherwise OOD generalization is impossible. We prove that a form of the information bottleneck constraint along with invariance helps address key failures when invariant features capture all the information about the label and also retains the existing success when they do not.
  arXiv  Detail & Related papers  (2021-06-11T20:42:27Z)
• Deep learning: a statistical viewpoint [120.94133818355645]
  Deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-perfect solutions to non-optimal training problems. We conjecture that specific principles underlie these phenomena.
  arXiv  Detail & Related papers  (2021-03-16T16:26:36Z)
• Dimension Free Generalization Bounds for Non Linear Metric Learning [61.193693608166114]
  We provide uniform generalization bounds for two regimes -- the sparse regime, and a non-sparse regime. We show that by relying on a different, new property of the solutions, it is still possible to provide dimension free generalization guarantees.
  arXiv  Detail & Related papers  (2021-02-07T14:47:00Z)
• Optimal oracle inequalities for solving projected fixed-point equations [53.31620399640334]
  We study methods that use a collection of random observations to compute approximate solutions by searching over a known low-dimensional subspace of the Hilbert space. We show how our results precisely characterize the error of a class of temporal difference learning methods for the policy evaluation problem with linear function approximation.
  arXiv  Detail & Related papers  (2020-12-09T20:19:32Z)
• Integrable Nonparametric Flows [5.9774834479750805]
  We introduce a method for reconstructing an infinitesimal normalizing flow given only an infinitesimal change to a probability distribution. This reverses the conventional task of normalizing flows. We discuss potential applications to problems in quantum Monte Carlo and machine learning.
  arXiv  Detail & Related papers  (2020-12-03T16:19:52Z)
• Density Fixing: Simple yet Effective Regularization Method based on the Class Prior [2.3859169601259347]
  We propose a framework of regularization methods, called density-fixing, that can be used commonly for supervised and semi-supervised learning. Our proposed regularization method improves the generalization performance by forcing the model to approximate the class's prior distribution or the frequency of occurrence.
  arXiv  Detail & Related papers  (2020-07-08T04:58:22Z)
• Learning the Truth From Only One Side of the Story [58.65439277460011]
  We focus on generalized linear models and show that without adjusting for this sampling bias, the model may converge suboptimally or even fail to converge to the optimal solution. We propose an adaptive approach that comes with theoretical guarantees and show that it outperforms several existing methods empirically.
  arXiv  Detail & Related papers  (2020-06-08T18:20:28Z)
• Approximation Schemes for ReLU Regression [80.33702497406632]
  We consider the fundamental problem of ReLU regression. The goal is to output the best fitting ReLU with respect to square loss given to draws from some unknown distribution.
  arXiv  Detail & Related papers  (2020-05-26T16:26:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.