English
Related papers

Related papers: Marginals Before Conditionals

200 papers

Grokking is a puzzling phenomenon in neural networks where full generalization occurs only after a substantial delay following the complete memorization of the training data. Previous research has linked this delayed generalization to…

Machine Learning · Computer Science 2026-01-12 Tiberiu Musat

Noise is usually regarded as adversarial to extract the effective dynamics from time series, such that the conventional data-driven approaches usually aim at learning the dynamics by mitigating the noisy effect. However, noise can have a…

Adaptation and Self-Organizing Systems · Physics 2023-09-12 Zequn Lin , Zhaofan Lu , Zengru Di , Ying Tang

A new loss function is proposed for neural networks on classification tasks which extends the hinge loss by assigning gradients to its critical points. We will show that for a linear classifier on linearly separable data with fixed step…

Machine Learning · Computer Science 2020-06-26 Justin Lizama

The existence and characterisation of noise-driven bifurcations from the spatially homogeneous stationary states of a nonlinear, non-local Fokker--Planck type partial differential equation describing stochastic neural fields is established.…

Analysis of PDEs · Mathematics 2023-04-26 José A. Carrillo , Pierre Roux , Susanne Solem

Graph neural networks use relational information as an inductive bias to enhance prediction performance. Not rarely, task-relevant relations are unknown and graph structure learning approaches have been proposed to learn them from data.…

Machine Learning · Computer Science 2025-05-29 Alessandro Manenti , Daniele Zambon , Cesare Alippi

We initiate the study of stochastic optimization with oblivious noise, broadly generalizing the standard heavy-tailed noise setup. In our setting, in addition to random observation noise, the stochastic gradient may be subject to…

Data Structures and Algorithms · Computer Science 2024-08-06 Ilias Diakonikolas , Sushrut Karmalkar , Jongho Park , Christos Tzamos

We propose a novel family of decision-aware surrogate losses, called Perturbation Gradient (PG) losses, for the predict-then-optimize framework. The key idea is to connect the expected downstream decision loss with the directional…

Machine Learning · Computer Science 2024-11-01 Michael Huang , Vishal Gupta

Two main challenges preventing efficient training of variational quantum algorithms and quantum machine learning models are local minima and barren plateaus. Typically, barren plateaus are associated with deep circuits, while shallow…

Quantum Physics · Physics 2025-02-10 Nikita A. Nemkov , Evgeniy O. Kiktenko , Aleksey K. Fedorov

We study random walks on contingency tables with fixed marginals, corresponding to a (log-linear) hierarchical model. If the set of allowed moves is not a Markov basis, then there exist tables with the same marginals that are not connected.…

Commutative Algebra · Mathematics 2016-04-08 Thomas Kahle , Johannes Rauh , Seth Sullivant

Researchers illustrate improvements in contextual encoding strategies via resultant performance on a battery of shared Natural Language Understanding (NLU) tasks. Many of these tasks are of a categorical prediction variety: given a…

Computation and Language · Computer Science 2019-06-06 Zhongyang Li , Tongfei Chen , Benjamin Van Durme

Ranked decision systems -- recommenders, ad auctions, clinical triage queues -- must decide when to intervene in ranked outputs and when to abstain. We study when confidence-based abstention monotonically improves decision quality, and when…

Artificial Intelligence · Computer Science 2026-03-11 Ronald Doku

Bayesian networks (BNs) are a widely used class of probabilistic graphical models employed in numerous application domains. However, inferring the network's graphical structure from data remains challenging. Bayesian structure learners…

Machine Learning · Computer Science 2025-11-19 William Zhao , Guy Van den Broeck , Benjie Wang

In the sequential learning problem, agents in a network attempt to predict a binary ground truth, informed by both a noisy private signal and the predictions of neighboring agents before them. It is well known that social learning in this…

Social and Information Networks · Computer Science 2026-02-10 William Guo , Edward Xiong , Jie Gao

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

Conditional depth execution routes a subset of tokens through a lightweight cheap FFN while the remainder execute the standard full FFN at each controlled layer. The central difficulty is gate training: the gate decision must propagate…

Machine Learning · Computer Science 2026-04-21 Qingwei Lin

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Machine Learning · Computer Science 2026-05-08 Alaa Zniber , Ouassim Karrakchou , Mounir Ghogho

The multi-stage phenomenon in the training loss curves of neural networks has been widely observed, reflecting the non-linearity and complexity inherent in the training process. In this work, we investigate the training dynamics of neural…

Machine Learning · Computer Science 2024-11-07 Zheng-An Chen , Tao Luo , GuiHong Wang

We consider a neural network with adapting synapses whose dynamics can be analitically computed. The model is made of $N$ neurons and each of them is connected to $K$ input neurons chosen at random in the network. The synapses are…

Disordered Systems and Neural Networks · Physics 2009-10-30 G. Lattanzi , G. Nardulli , G. Pasquariello , S. Stramaglia

Double Machine Learning is often justified by nuisance-rate conditions, yet finite-sample reliability also depends on the conditioning of the orthogonal-score Jacobian. This conditioning is typically assumed rather than tracked. When…

Methodology · Statistics 2026-01-08 Gabriel Saco

Noise-tolerant PAC learning of linear models has been of central interests in machine learning community since the last century. In recent years, many computationally-efficient algorithms have been proposed for the problem of learning…

Machine Learning · Computer Science 2026-05-19 Rita Adhikari , Shiwei Zeng