English
Related papers

Related papers: Maximum Spanning Trees Are Invariant to Temperatur…

200 papers

A line of recent works established that when training linear predictors over separable data, using gradient methods and exponentially-tailed losses, the predictors asymptotically converge in direction to the max-margin predictor. As a…

Machine Learning · Computer Science 2020-09-11 Ohad Shamir

We study the problem of entropy calibration, which asks whether a language model's entropy over generations matches its log loss on human text. Past work found that models are miscalibrated, with entropy per step increasing as generations…

Computation and Language · Computer Science 2026-01-14 Steven Cao , Gregory Valiant , Percy Liang

Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the…

Machine Learning · Computer Science 2019-05-10 Azadeh Sadat Mozafari , Hugo Siqueira Gomes , Wilson Leão , Steeven Janny , Christian Gagné

We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees. This not only establishes a theoretical relation between transition-based parsing and…

Computation and Language · Computer Science 2020-11-03 Carlos Gómez-Rodríguez , Michalina Strzyz , David Vilares

Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures. Many such structured-prediction problems require…

Computation and Language · Computer Science 2019-04-23 Jay Yoon Lee , Sanket Vaibhav Mehta , Michael Wick , Jean-Baptiste Tristan , Jaime Carbonell

Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient calibration methods for neural networks is therefore an…

Machine Learning · Computer Science 2023-09-07 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

A tree $\sigma$-spanner of a positively real-weighted $n$-vertex and $m$-edge undirected graph $G$ is a spanning tree $T$ of $G$ which approximately preserves (i.e., up to a multiplicative stretch factor $\sigma$) distances in $G$. Tree…

Data Structures and Algorithms · Computer Science 2017-10-05 Davide Bilò , Feliciano Colella , Luciano Gualà , Stefano Leucci , Guido Proietti

Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic regression can be motivated from a simple theoretical…

Machine Learning · Computer Science 2026-03-11 Eugène Berta , David Holzmüller , Michael I. Jordan , Francis Bach

Spreading processes on graphs arise in a host of application domains, from the study of online social networks to viral marketing to epidemiology. Various discrete-time probabilistic models for spreading processes have been proposed. These…

Social and Information Networks · Computer Science 2021-09-24 Abram Magner , Carolyn Kaminski , Petko Bogdanov

A tree $t$-spanner of a graph $G$ is a spanning tree of $G$ such that the distance between pairs of vertices in the tree is at most $t$ times their distance in $G$. Deciding tree $t$-spanner admissible graphs has been proved to be tractable…

Discrete Mathematics · Computer Science 2018-01-01 Ioannis Papoutsakis

We investigate the parameter space of transformer models trained on protein sequence data using a statistical mechanics framework, sampling the loss landscape at varying temperatures by Langevin dynamics to characterize the low-loss…

Disordered Systems and Neural Networks · Physics 2026-04-01 L. Ghiringhelli , A. Zambon , G. Tiana

Recent advancements in pre-trained language models (PLMs) have demonstrated that these models possess some degree of syntactic awareness. To leverage this knowledge, we propose a novel chart-based method for extracting parse trees from…

Computation and Language · Computer Science 2023-06-02 Jiaxi Li , Wei Lu

Max-stable processes are increasingly widely used for modelling complex extreme events, but existing fitting methods are computationally demanding, limiting applications to a few dozen variables. $r$-Pareto processes are mathematically…

Methodology · Statistics 2017-06-14 Raphaël de Fondeville , Anthony C. Davison

Decision trees are ubiquitous in machine learning for their ease of use and interpretability. Yet, these models are not typically employed in reinforcement learning as they cannot be updated online via stochastic gradient descent. We…

Machine Learning · Computer Science 2020-06-29 Andrew Silva , Taylor Killian , Ivan Dario Jimenez Rodriguez , Sung-Hyun Son , Matthew Gombolay

To understand how well a large language model captures certain semantic or syntactic features, researchers typically apply probing classifiers. However, the accuracy of these classifiers is critical for the correct interpretation of the…

Computation and Language · Computer Science 2023-12-19 Sergey A. Saltykov

We investigate the maximum caliber variational principle as an inference algorithm used to predict dynamical properties of complex nonequilibrium, stationary, statistical systems in the presence of incomplete information. Specifically, we…

Statistical Mechanics · Physics 2016-12-28 Carlo Cafaro , Sean Alan Ali

Sampling is a fundamental problem in computer science and statistics. However, for a given task and stream, it is often not possible to choose good sampling probabilities in advance. We derive a general framework for adaptively changing the…

Machine Learning · Statistics 2022-06-16 Daniel Ting

This work describes probabilistic methods for utilizing random spanning trees generated via a random walk process. Goyal et al. showed that the union of random spanning trees approximates the expansion of every cut of a graph. First, we…

Networking and Internet Architecture · Computer Science 2019-10-16 Shlomi Dolev , Daniel Khankin

Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an effective tool for…

Computation and Language · Computer Science 2022-01-28 Bin Li , Yunlong Fan , Yikemaiti Sataer , Zhiqiang Gao

We compare the performance of a transition-based parser in regards to different annotation schemes. We pro-pose to convert some specific syntactic constructions observed in the universal dependency treebanks into a so-called more standard…

Computation and Language · Computer Science 2025-03-11 Guillaume Wisniewski , Ophélie Lacroix
‹ Prev 1 4 5 6 7 8 10 Next ›