English
Related papers

Related papers: Exchangeability and Kernel Invariance in Trained M…

200 papers

Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes. However, in physical neural systems such as the brain, weight-sharing is implausible. This discrepancy raises the fundamental question of whether…

Machine Learning · Computer Science 2019-10-08 Jordan Ott , Erik Linstead , Nicholas LaHaye , Pierre Baldi

This note continues study of exchangeability martingales, i.e., processes that are martingales under any exchangeable distribution for the observations. Such processes can be used for detecting violations of the IID assumption, which is…

Machine Learning · Computer Science 2020-12-29 Vladimir Vovk

As deep neural networks grow in size, from thousands to millions to billions of weights, the performance of those networks becomes limited by our ability to accurately train them. A common naive question arises: if we have a system with…

Machine Learning · Computer Science 2018-05-29 Nathan O. Hodas , Panos Stinis

Pretrained Transformers demonstrate remarkable in-context learning (ICL) capabilities, enabling them to adapt to new tasks from demonstrations without parameter updates. However, theoretical studies often rely on simplified architectures…

Machine Learning · Statistics 2026-02-06 Samet Demir , Zafer Dogan

Despite the tremendous successes of deep neural networks (DNNs) in various applications, many fundamental aspects of deep learning remain incompletely understood, including DNN trainability. In a trainability study, one aims to discern what…

Machine Learning · Computer Science 2023-05-19 Yueyao Yu , Yin Zhang

Covariate shift relaxes the widely-employed independent and identically distributed (IID) assumption by allowing different training and testing input distributions. Unfortunately, common methods for addressing covariate shift by trying to…

Machine Learning · Computer Science 2018-01-02 Anqi Liu , Brian D. Ziebart

Recent studies have shown that high disparities in effective learning rates (ELRs) across layers in deep neural networks can negatively affect trainability. We formalize how these disparities evolve over time by modeling weight dynamics…

Machine Learning · Computer Science 2024-05-27 Christian H. X. Ali Mehmeti-Göpel , Michael Wand

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

Whether deep neural networks can exhibit emergent behaviour is not only relevant for understanding how deep learning works, it is also pivotal for estimating potential security risks of increasingly capable artificial intelligence systems.…

Machine Learning · Computer Science 2025-04-11 Pascal de Jong , Felix Meigel , Steffen Rulands

In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models. In this work, we follow the setting proposed in…

Machine Learning · Computer Science 2023-05-29 Kartik Ahuja , David Lopez-Paz

Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed beliefs and…

Machine Learning · Statistics 2024-12-02 Naimeng Ye , Hongseok Namkoong

Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting distance between distributions, are useful tools for fully nonparametric two-sample testing and learning on distributions. However, it is rarely that…

Machine Learning · Statistics 2017-11-07 Ho Chung Leon Law , Christopher Yau , Dino Sejdinovic

Model reparametrization, which follows the change-of-variable rule of calculus, is a popular way to improve the training of neural nets. But it can also be problematic since it can induce inconsistencies in, e.g., Hessian-based flatness…

Machine Learning · Computer Science 2023-10-24 Agustinus Kristiadi , Felix Dangel , Philipp Hennig

Matching two different sets of items, called heterogeneous set-to-set matching problem, has recently received attention as a promising problem. The difficulties are to extract features to match a correct pair of different sets and also…

Computer Vision and Pattern Recognition · Computer Science 2021-01-29 Yuki Saito , Takuma Nakamura , Hirotaka Hachiya , Kenji Fukumizu

Many machine learning methods assume that the training and test data follow the same distribution. However, in the real world, this assumption is very often violated. In particular, the phenomenon that the marginal distribution of the data…

Machine Learning · Computer Science 2023-04-20 Masanari Kimura , Hideitsu Hino

Symmetry is present in nature and science. In image processing, kernels for spatial filtering possess some symmetry (e.g. Sobel operators, Gaussian, Laplacian). Convolutional layers in artificial feed-forward neural networks have typically…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Gregory Dzhezyan , Hubert Cecotti

Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either empirical behaviour, leaving them blind to…

Machine Learning · Computer Science 2026-05-15 ML Nissen Gonzalez , Melwina Albuquerque , Laurence Wroe , Jacob Meyer Cohen , Logan Riggs Smith , Thomas Dooms

Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 David M. Knigge , David W. Romero , Erik J. Bekkers

In Bayesian multilevel models, the data are structured in interconnected groups, and their posteriors borrow information from one another due to prior dependence between latent parameters. However, little is known about the behaviour of the…

Statistics Theory · Mathematics 2025-09-25 Marta Catalano , Hugo Lavenant , Francesco Mascari

Linear Mode Connectivity (LMC) refers to the phenomenon that performance remains consistent for linearly interpolated models in the parameter space. For independently optimized model pairs from different random initializations, achieving…

Machine Learning · Computer Science 2025-02-17 Ryuichi Kanoh , Mahito Sugiyama