English
Related papers

Related papers: Interpretability Illusions in the Generalization o…

200 papers

Is a deep learning model capable of understanding systems governed by certain first principle laws by only observing the system's output? Can deep learning learn the underlying physics and honor the physics when making predictions? The…

Computational Physics · Physics 2020-06-11 Rohan Thavarajah , Xiang Zhai , Zheren Ma , David Castineira

While there are many applications of ML to scientific problems that look promising, visuals can be deceiving. Using numerical analysis techniques, we rigorously quantify the accuracy, convergence rates, and generalization bounds of certain…

Machine Learning · Computer Science 2026-05-27 Alejandro Francisco Queiruga , Theo Gutman-Solo , Shuai Jiang

Learning on synthetic data and transferring the resulting properties to their real counterparts is an important challenge for reducing costs and increasing safety in machine learning. In this work, we focus on autoencoder architectures and…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Steve Dias Da Cruz , Bertram Taetz , Thomas Stifter , Didier Stricker

The lack of interpretability remains a key barrier to the adoption of deep models in many applications. In this work, we explicitly regularize deep models so human users might step through the process behind their predictions in little…

Machine Learning · Statistics 2017-11-17 Mike Wu , Michael C. Hughes , Sonali Parbhoo , Maurizio Zazzi , Volker Roth , Finale Doshi-Velez

Interpretability research often aims to predict how a model will respond to targeted interventions on specific mechanisms. However, it rarely predicts how a model will respond to unseen input data. This paper explores the promises and…

Machine Learning · Computer Science 2025-07-10 Victoria R. Li , Jenny Kaufmann , Martin Wattenberg , David Alvarez-Melis , Naomi Saphra

Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events. While distributional models -- most recently pre-trained, Transformer language models -- have demonstrated…

Computation and Language · Computer Science 2021-04-22 Ian Porada , Kaheer Suleman , Adam Trischler , Jackie Chi Kit Cheung

Deep networks often exhibit a preference for "simple" solutions, and such a simplicity bias is widely believed to play a key role in generalization. Yet a broadly applicable, quantitative measure of simplicity remains elusive. We introduce…

Artificial Intelligence · Computer Science 2026-05-29 Tianren Zhang , Xiangxin Li , Minghao Xiao , Guanyu Chen , Feng Chen

In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework…

Machine Learning · Computer Science 2018-11-09 Shengjia Zhao , Hongyu Ren , Arianna Yuan , Jiaming Song , Noah Goodman , Stefano Ermon

Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…

Machine Learning · Statistics 2018-02-27 Fredrik D. Johansson , Nathan Kallus , Uri Shalit , David Sontag

Diffusion models are powerful generative models that produce high-quality samples from complex data. While their infinite-data behavior is well understood, their generalization with finite data remains less clear. Classical learning theory…

Machine Learning · Statistics 2026-02-02 Claudia Merger , Sebastian Goldt

Embedding 3D morphable basis functions into deep neural networks opens great potential for models with better representation power. However, to faithfully learn those models from an image collection, it requires strong regularization to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-11 Luan Tran , Feng Liu , Xiaoming Liu

This paper presents a novel framework for demystification of convolutional deep learning models for time-series analysis. This is a step towards making informed/explainable decisions in the domain of time-series, powered by deep learning.…

Machine Learning · Computer Science 2020-05-06 Shoaib Ahmed Siddiqui , Dominik Mercier , Mohsin Munir , Andreas Dengel , Sheraz Ahmed

Unsupervised and self-supervised learning approaches have become a crucial tool to learn representations for downstream prediction tasks. While these approaches are widely used in practice and achieve impressive empirical gains, their…

Machine Learning · Computer Science 2020-10-23 Siddhant Garg , Yingyu Liang

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…

Artificial Intelligence · Computer Science 2022-02-23 Diego Gomez , Nicanor Quijano , Luis Felipe Giraldo

Deep learning Networks play a crucial role in the evolution of a vast number of current machine learning models for solving a variety of real world non-trivial tasks. Such networks use big data which is generally unlabeled unsupervised and…

Neural and Evolutionary Computing · Computer Science 2015-06-26 N. E. Osegi , P. Enyindah

Deep neural networks have demonstrated remarkable performance across various domains, yet their decision-making processes remain opaque. Although many explanation methods are dedicated to bringing the obscurity of DNNs to light, they…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Kanglong Fan , Yunqiao Yang , Chen Ma

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…

Machine Learning · Computer Science 2022-04-05 Pedro Sandoval-Segura , Wallace Lawson

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning…

In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where each original input datapoint is described by a set of vectors and their associated outputs may be given by soft…

Machine Learning · Computer Science 2012-06-22 Edwin Bonilla , Antonio Robles-Kelly