English
Related papers

Related papers: Tokens-per-Parameter Coverage Is Critical for Robu…

200 papers

Scaling Laws have emerged as a powerful framework for understanding how model performance evolves as they increase in size, providing valuable insights for optimizing computational resources. In the realm of Sequential Recommendation (SR),…

Artificial Intelligence · Computer Science 2025-02-20 Tingjia Shen , Hao Wang , Chuhan Wu , Jin Yao Chin , Wei Guo , Yong Liu , Huifeng Guo , Defu Lian , Ruiming Tang , Enhong Chen

Deep learning has achieved many breakthroughs in modern classification tasks. Numerous architectures have been proposed for different data structures but when it comes to the loss function, the cross-entropy loss is the predominant choice.…

Machine Learning · Statistics 2021-12-08 Tianyang Hu , Jun Wang , Wenjia Wang , Zhenguo Li

Shaping gain is attained in schemes where a shaped subcode is chosen from a larger codebook by a codeword selection process. This includes the popular method of Trellis Shaping (TS), originally proposed by Forney for average power…

Information Theory · Computer Science 2013-08-28 Stella Achtenberg , Dan Raphaeli

Gradient-based local optimization has been shown to improve results of genetic programming (GP) for symbolic regression. Several state-of-the-art GP implementations use iterative nonlinear least squares (NLS) algorithms such as the…

Neural and Evolutionary Computing · Computer Science 2023-06-21 Gabriel Kronberger

Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large language models (LLMs). This is done either by fitting a scaling law to the hyperparameters…

Machine Learning · Computer Science 2026-05-21 Dayal Singh Kalra , Maissam Barkeshli

Next-token prediction (NTP) over large text corpora has become the go-to paradigm to train large language models. Yet, it remains unclear how NTP influences the mapping of linguistic patterns to geometric properties of the resulting model…

Computation and Language · Computer Science 2025-02-20 Yize Zhao , Tina Behnia , Vala Vakilian , Christos Thrampoulidis

Large language models (LLMs) increasingly follow neural scaling laws that tie performance gains to rapidly expanding computational budgets, raising concerns about the sustainability of frontier-scale training. Existing carbon-estimation…

Computation and Language · Computer Science 2026-05-19 Lei Jiang , Fan Chen

Alternatives to backpropagation have long been studied to better understand how biological brains may learn. Recently, they have also garnered interest as a way to train neural networks more efficiently. By relaxing constraints inherent to…

Machine Learning · Computer Science 2022-10-27 Matthew J. Filipovich , Alessandro Cappelli , Daniel Hesslow , Julien Launay

Nonlinear model predictive control~(NMPC) generally requires the solution of a non-convex optimization problem at each sampling instant under strict timing constraints, based on a set of differential equations that can often be stiff and/or…

Optimization and Control · Mathematics 2019-03-22 Pedro Hespanhol , Rien Quirynen

Machine learning models are vulnerable to adversarial perturbations, and a thought-provoking paper by Bubeck and Sellke has analyzed this phenomenon through the lens of over-parameterization: interpolating smoothly the data requires…

Machine Learning · Statistics 2023-05-30 Simone Bombari , Shayan Kiyani , Marco Mondelli

Deep neural networks trained end-to-end to map a measurement of a (noisy) image to a clean image perform excellent for a variety of linear inverse problems. Current methods are only trained on a few hundreds or thousands of images as…

Image and Video Processing · Electrical Eng. & Systems 2023-02-24 Tobit Klug , Reinhard Heckel

Presently, topology optimization requires multiple iterations to create an optimized structure for given conditions. Among the conditions for topology optimization,the design area is one of the most important for structural design. In this…

Computational Engineering, Finance, and Science · Computer Science 2020-04-21 Keigo Nakamura , Yoshiro Suzuki

This work studies the combinatorial optimization problem of finding an optimal core tensor shape, also called multilinear rank, for a size-constrained Tucker decomposition. We give an algorithm with provable approximation guarantees for its…

Data Structures and Algorithms · Computer Science 2024-06-19 Mehrdad Ghadiri , Matthew Fahrbach , Gang Fu , Vahab Mirrokni

It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more…

Machine Learning · Computer Science 2023-06-07 Sadhika Malladi , Alexander Wettig , Dingli Yu , Danqi Chen , Sanjeev Arora

Large language models have demonstrated predictable scaling behaviors with respect to model parameters and training data. This study investigates whether a similar scaling relationship exist for vision-language models with respect to the…

Artificial Intelligence · Computer Science 2025-12-30 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Qibin Zhao

We show that the scaling laws which determine the performance of large language models (LLMs) severely limit their ability to improve the uncertainty of their predictions. As a result, raising their reliability to meet the standards of…

Artificial Intelligence · Computer Science 2025-07-31 Peter V. Coveney , Sauro Succi

Reinforcement learning methods typically use Deep Neural Networks to approximate the value functions and policies underlying a Markov Decision Process. Unfortunately, DNN-based RL suffers from a lack of explainability of the resulting…

Systems and Control · Electrical Eng. & Systems 2022-05-19 Shambhuraj Sawant , Sebastien Gros

This work blends the inexact Newton method with iterative combined approximations (ICA) for solving topology optimization problems under the assumption of geometric nonlinearity. The density-based problem formulation is solved using a…

Numerical Analysis · Mathematics 2021-12-17 Thadeu A. Senne , Francisco A. M. Gomes , Sandra A. Santos

This paper investigates model reduction methods for efficiently approximating the solution of parameter-dependent PDEs with a multi-parameter vector $\vec{\mu} \in \mathbb{R}^p$. In cases where the Kolmogorov $N$-width decays fast enough,…

Numerical Analysis · Mathematics 2026-01-21 Joubine Aghili , Hassan Ballout , Yvon Maday , Christophe Prud'homme

The success of large-scale language models like GPT can be attributed to their ability to efficiently predict the next token in a sequence. However, these models rely on constant computational effort regardless of the complexity of the…

Artificial Intelligence · Computer Science 2024-11-11 Kei-Sing Ng , Qingchen Wang