English
Related papers

Related papers: Tractable Sharpness-Aware Learning of Probabilisti…

200 papers

The past decade has seen a significant interest in learning tractable probabilistic representations. Arithmetic circuits (ACs) were among the first proposed tractable representations, with some subsequent representations being instances of…

Artificial Intelligence · Computer Science 2017-08-25 Arthur Choi , Adnan Darwiche

Over-parameterized neural networks generalize well in practice without any explicit regularization. Although it has not been proven yet, empirical evidence suggests that implicit regularization plays a crucial role in deep learning and…

Machine Learning · Computer Science 2019-03-07 Masayoshi Kubo , Ryotaro Banno , Hidetaka Manabe , Masataka Minoji

Neural networks are powerful function approximators with tremendous potential in learning complex distributions. However, they are prone to overfitting on spurious patterns. Bayesian inference provides a principled way to regularize neural…

Machine Learning · Computer Science 2024-12-02 Yanzhe Bekkemoen , Helge Langseth

With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature…

Machine Learning · Computer Science 2019-01-08 Tsui-Wei Weng , Pin-Yu Chen , Lam M. Nguyen , Mark S. Squillante , Ivan Oseledets , Luca Daniel

The largest eigenvalue of the Hessian, or sharpness, of neural networks is a key quantity to understand their optimization dynamics. In this paper, we study the sharpness of deep linear networks for univariate regression. Minimizers can…

Machine Learning · Statistics 2024-10-29 Pierre Marion , Lénaïc Chizat

We consider the task of estimating a high-dimensional directed acyclic graph, given observations from a linear structural equation model with arbitrary noise distribution. By exploiting properties of common random graphs, we develop a new…

Machine Learning · Statistics 2019-12-30 Arjun Sondhi , Ali Shojaie

Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling…

Recent research in robust optimization has shown an overfitting-like phenomenon in which models trained against adversarial attacks exhibit higher robustness on the training set compared to the test set. Although previous work provided…

Machine Learning · Computer Science 2022-11-24 Zifan Wang , Nan Ding , Tomer Levinboim , Xi Chen , Radu Soricut

Probabilistic circuits (PCs) are a class of tractable probabilistic models, which admit efficient inference routines depending on their structural properties. In this paper, we introduce md-vtrees, a novel structural formulation of…

Artificial Intelligence · Computer Science 2023-04-18 Benjie Wang , Marta Kwiatkowska

Probabilistic circuits (PCs) are a class of tractable probabilistic models that allow efficient, often linear-time, inference of queries such as marginals and most probable explanations (MPE). However, marginal MAP, which is central to many…

Artificial Intelligence · Computer Science 2022-03-07 YooJung Choi , Tal Friedman , Guy Van den Broeck

Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model calibration techniques mitigate the problem of…

Machine Learning · Computer Science 2022-12-21 Ramya Hebbalaguppe , Rishabh Patra , Tirtharaj Dash , Gautam Shroff , Lovekesh Vig

Data-driven predictive control (DPC), using linear combinations of recorded trajectory data, has recently emerged as a popular alternative to traditional model predictive control (MPC). Without an explicitly enforced prediction model, the…

Systems and Control · Electrical Eng. & Systems 2025-03-31 Manuel Klädtke , Moritz Schulze Darup

We here adapt an extended version of the adaptive cubic regularisation method with dynamic inexact Hessian information for nonconvex optimisation in [3] to the stochastic optimisation setting. While exact function evaluations are still…

Numerical Analysis · Mathematics 2020-09-15 Stefania Bellavia , Gianmarco Gurioli

Partition of unity networks (POU-Nets) have been shown capable of realizing algebraic convergence rates for regression and solution of PDEs, but require empirical tuning of training parameters. We enrich POU-Nets with a Gaussian noise model…

Machine Learning · Computer Science 2021-07-08 Nat Trask , Mamikon Gulian , Andy Huang , Kookjin Lee

Probabilistic models based on continuous latent spaces, such as variational autoencoders, can be understood as uncountable mixture models where components depend continuously on the latent code. They have proven to be expressive tools for…

Machine Learning · Computer Science 2024-06-27 Alvaro H. C. Correia , Gennaro Gala , Erik Quaeghebeur , Cassio de Campos , Robert Peharz

Inference in discrete graphical models with variational methods is difficult because of the inability to re-parameterize gradients of the Evidence Lower Bound (ELBO). Many sampling-based methods have been proposed for estimating these…

Machine Learning · Computer Science 2020-10-23 Andy Shih , Stefano Ermon

A fundamental challenge in probabilistic modeling is to balance expressivity and inference efficiency. Tractable probabilistic models (TPMs) aim to directly address this tradeoff by imposing constraints that guarantee efficient inference of…

Artificial Intelligence · Computer Science 2025-10-28 John Leland , YooJung Choi

This paper proposes an Adaptive Learning Model Predictive Control strategy for uncertain constrained linear systems performing iterative tasks. The additive uncertainty is modeled as the sum of a bounded process noise and an unknown…

Systems and Control · Computer Science 2018-04-27 Monimoy Bujarbaruah , Xiaojing Zhang , Ugo Rosolia , Francesco Borrelli

Brittle optimization has been observed to adversely impact model likelihoods for regression and VAEs when simultaneously fitting neural network mappings from a (random) variable onto the mean and variance of a dependent Gaussian variable.…

Machine Learning · Computer Science 2020-11-02 Andrew Stirn , David A. Knowles

Gaussian process classification (GPC) provides a flexible and powerful statistical framework describing joint distributions over function space. Conventional GPCs however suffer from (i) poor scalability for big data due to the full kernel…

Machine Learning · Statistics 2019-09-17 Haitao Liu , Yew-Soon Ong , Ziwei Yu , Jianfei Cai , Xiaobo Shen