English
Related papers

Related papers: Marginals Before Conditionals

200 papers

Autonomous (noise-agnostic) generative models, such as Equilibrium Matching and blind diffusion, challenge the standard paradigm by learning a single, time-invariant vector field that operates without explicit noise-level conditioning.…

Machine Learning · Computer Science 2026-02-23 Mojtaba Sahraee-Ardakan , Mauricio Delbracio , Peyman Milanfar

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

The dynamical organization in the presence of noise of a Boolean neural network with random connections is analyzed. For low levels of noise, the system reaches a stationary state in which the majority of its elements acquire the same…

Disordered Systems and Neural Networks · Physics 2007-05-23 Cristian Huepe , Maximino Aldana

Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes…

Machine Learning · Computer Science 2025-03-25 Raphaël Berthier , Andrea Montanari , Kangjie Zhou

In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input$\unicode{x2013}$output…

Machine Learning · Computer Science 2026-05-25 Vincent C. Brockers , Roman D. Ventzke , Valentin Neuhaus , Belén Hidalgo-Ogalde , Viola Priesemann

In this paper, we study the implicit regularization of the gradient descent algorithm in homogeneous neural networks, including fully-connected and convolutional neural networks with ReLU or LeakyReLU activations. In particular, we study…

Machine Learning · Computer Science 2021-01-01 Kaifeng Lyu , Jian Li

A deep neural network trained on noisy labels is known to quickly lose its power to discriminate clean instances from noisy ones. After the early learning phase has ended, the network memorizes the noisy instances, which leads to a…

Machine Learning · Computer Science 2021-09-03 Jason Z. Lin , Jelena Bradic

The typical training of neural networks using large stepsize gradient descent (GD) under the logistic loss often involves two distinct phases, where the empirical risk oscillates in the first phase but decreases monotonically in the second…

Machine Learning · Statistics 2024-06-28 Yuhang Cai , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

Selective classifiers improve model reliability by abstaining on inputs the model deems uncertain. However, few practical approaches achieve the gold-standard performance of a perfect-ordering oracle that accepts examples exactly in order…

Machine Learning · Computer Science 2025-10-27 Stephan Rabanser , Nicolas Papernot

Goal-conditioned systems assume goals are provided externally. We ask whether attentional priorities can emerge endogenously from an agent's internal cognitive state. We propose a priority function that generates observation targets from…

Artificial Intelligence · Computer Science 2026-03-11 Zhuoran Deng , Yizhi Zhang , Ziyi Zhang , Wan Shen

The traditional two-stage approach to causal inference first identifies a single causal model (or equivalence class of models), which is then used to answer causal queries. However, this neglects any epistemic model uncertainty. In…

Machine Learning · Computer Science 2025-04-25 Christian Toth , Christian Knoll , Franz Pernkopf , Robert Peharz

We present a loss function for neural networks that encompasses an idea of trivial versus non-trivial predictions, such that the network jointly determines its own prediction goals and learns to satisfy them. This permits the network to…

Artificial Intelligence · Computer Science 2016-12-15 Nicholas Guttenberg , Martin Biehl , Ryota Kanai

Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Davide Abati , Jakub Tomczak , Tijmen Blankevoort , Simone Calderara , Rita Cucchiara , Babak Ehteshami Bejnordi

Learning and decision making in the brain are key processes critical to survival, and yet are processes implemented by non-ideal biological building blocks which can impose significant error. We explore quantitatively how the brain might…

Neurons and Cognition · Quantitative Biology 2011-04-19 Jake Bouvrie , Jean-Jacques Slotine

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem…

Machine Learning · Computer Science 2019-09-10 Mo Zhou , Tianyi Liu , Yan Li , Dachao Lin , Enlu Zhou , Tuo Zhao

Neural network training is typically viewed as gradient descent on a loss surface. We propose a fundamentally different perspective: learning is a structure-preserving transformation (a functor L) between the space of network parameters…

Machine Learning · Computer Science 2025-10-07 Abdulrahman Tamim

Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes representations, and why these representations support complex behavior remains incomplete. We…

Machine Learning · Computer Science 2026-05-14 Yifan Zhang

We develop the first active learning method for contextual linear optimization. Specifically, we introduce a label acquisition algorithm that sequentially decides whether to request the ``labels'' of feature samples from an unlabeled data…

Machine Learning · Computer Science 2025-01-31 Mo Liu , Paul Grigas , Heyuan Liu , Zuo-Jun Max Shen

Marginal models involve restrictions on the conditional and marginal association structure of a set of categorical variables. They generalize log-linear models for contingency tables, which are the fundamental tools for modelling the…

Methodology · Statistics 2023-04-10 Tamas Rudas , Wicher Bergsma

Training Transformers on algorithmic tasks frequently demonstrates an intriguing abrupt learning phenomenon: an extended performance plateau followed by a sudden, sharp improvement. This work investigates the underlying mechanisms for such…

Machine Learning · Computer Science 2025-10-24 Pulkit Gopalani , Wei Hu
‹ Prev 1 2 3 10 Next ›