English
Related papers

Related papers: Lower and Upper Bounds on CSL Parameters from Late…

200 papers

Sensitivity measures how much the output of an algorithm changes, in terms of Hamming distance, when part of the input is modified. While approximation algorithms with low sensitivity have been developed for many problems, no sensitivity…

Data Structures and Algorithms · Computer Science 2025-10-17 Noah Fleming , Yuichi Yoshida

High-throughput interpretation of robotically gathered seafloor visual imagery can increase the efficiency of marine monitoring and exploration. Although recent research has suggested that location metadata can enhance self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Cailei Liang , Adrian Bodenmann , Emma J Curtis , Samuel Simmons , Kazunori Nagano , Stan Brown , Adam Riese , Blair Thornton

We introduce Transductive Local Complexity (TLC) to extend the classical Local Rademacher Complexity (LRC) to the transductive setting, incorporating substantial and novel components. Although LRC has been used to obtain sharp…

Machine Learning · Statistics 2026-02-06 Yingzhen Yang

Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models. However, the high memory costs associated with fine-tuning remain…

Machine Learning · Computer Science 2025-02-04 David H. Yang , Mohammad Mohammadi Amiri , Tejaswini Pedapati , Subhajit Chaudhury , Pin-Yu Chen

We consider convection in an internally heated layer of fluid that is bounded below by a perfect insulator and above by a poor conductor. The poorly conducting boundary is modelled by a fixed heat flux. Using solely analytical methods, we…

Fluid Dynamics · Physics 2016-06-30 David Goluskin

We consider the problem of high-dimensional filtering of state-space models (SSMs) at discrete times. This problem is particularly challenging as analytical solutions are typically not available and many numerical approximation methods can…

Computation · Statistics 2022-01-13 Hamza Ruzayqat , Aimad Er-Raiy , Alexandros Beskos , Dan Crisan , Ajay Jasra , Nikolas Kantas

Matrix-level low-rank compression is a promising way to reduce the cost of large language models, but running compression and evaluating the resulting models on language tasks can be prohibitively expensive. Can compression-induced…

Machine Learning · Computer Science 2026-04-21 Mingxue Xu

In this paper we discuss a method, which we call Minimum Conditional Description Length (MCDL), for estimating the parameters of a subset of sites within a Markov random field. We assume that the edges are known for the entire graph…

Information Theory · Computer Science 2016-02-25 Matthew G. Reyes , David L. Neuhoff

Cosmological $\alpha$-attractors are a compelling class of inflationary models. They lead to universal predictions for large-scale observables, broadly independent from the functional form of the inflaton potential. In this work we derive…

Cosmology and Nongalactic Astrophysics · Physics 2023-09-21 Laura Iacconi , Matteo Fasiello , Jussi Väliviita , David Wands

Modern generative and vision-language models (VLMs) are increasingly used in scientific and medical decision support, where predicted probabilities must be both accurate and well calibrated. Despite strong empirical results with moderate…

Machine Learning · Computer Science 2025-12-30 Paul M. Thompson

Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained models assign high probability to plausible sequences given the…

Computation and Language · Computer Science 2022-10-04 Yao Zhao , Misha Khalman , Rishabh Joshi , Shashi Narayan , Mohammad Saleh , Peter J. Liu

The tremendous success of Transformer models in fields such as large language models and computer vision necessitates a rigorous theoretical investigation. To the best of our knowledge, this paper is the first work proving that standard…

Machine Learning · Statistics 2026-02-25 Yanming Lai , Defeng Sun

LDPC codes play a vital role in coding theory and practical error correction. A central problem in this direction is to understand their rate--distance tradeoff. In this paper, we introduce a new framework for estimating ball sizes in the…

Information Theory · Computer Science 2026-05-05 Chong Shangguan , Yulin Yang

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

Typical behavior of the linear programming (LP) problem is studied as a relaxation of the minimum vertex cover, a type of integer programming (IP) problem. A lattice-gas model on the Erd\"os-R\'enyi random graphs of $\alpha$-uniform…

Disordered Systems and Neural Networks · Physics 2016-06-01 Satoshi Takabe , Koji Hukushima

The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources. Yet, while empirically validated, its theoretical underpinnings remain poorly…

Machine Learning · Computer Science 2026-02-03 Chiwun Yang

In representation learning, Convolutional Sparse Coding (CSC) enables unsupervised learning of features by jointly optimising both an \(\ell_2\)-norm fidelity term and a sparsity enforcing penalty. This work investigates using a…

Image and Video Processing · Electrical Eng. & Systems 2021-07-15 Perla Mayo , Oktay Karakuş , Robin Holmes , Alin Achim

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their scalability raises a critical question: Have we reached the scaling ceiling? This paper addresses this pivotal question by developing a unified theoretical…

Machine Learning · Computer Science 2024-12-24 Charles Luo

Current cosmological tensions motivate investigating extensions to the standard $\Lambda$CDM model. Additional model parameters are typically varied one or two at a time, in a series of separate tests. The purpose of this paper is to…

Cosmology and Nongalactic Astrophysics · Physics 2020-08-11 Yajing Huang , Graeme Addison , Charles Bennett

A locally recoverable code (LRC code) is a code over a finite alphabet such that every symbol in the encoding is a function of a small number of other symbols that form a recovering set. In this paper we derive new finite-length and…

Information Theory · Computer Science 2016-03-10 Itzhak Tamo , Alexander Barg , Alexey Frolov
‹ Prev 1 3 4 5 6 7 10 Next ›