English
Related papers

Related papers: Learning in High Dimension Always Amounts to Extra…

200 papers

Continual learning is the ability to acquire new knowledge without forgetting the previously learned one, assuming no further access to past training data. Neural network approximators trained with gradient descent are known to fail in this…

Machine Learning · Computer Science 2021-11-05 Rodrigue Siry

Modern practice for training classification deepnets involves a Terminal Phase of Training (TPT), which begins at the epoch where training error first vanishes; During TPT, the training error stays effectively zero while training loss is…

Machine Learning · Computer Science 2020-09-23 Vardan Papyan , X. Y. Han , David L. Donoho

Deep learning has transformed computer vision, natural language processing, and speech recognition\cite{badrinarayanan2017segnet, dong2016image, ren2017faster, ji20133d}. However, two critical questions remain obscure: (1) why do deep…

Machine Learning · Statistics 2018-10-03 Jingwei Zhang , Tongliang Liu , Dacheng Tao

Matrices resulting from the discretization of a kernel function, e.g., in the context of integral equations or sampling probability distributions, can frequently be approximated by interpolation. In order to improve the efficiency, a…

Numerical Analysis · Mathematics 2021-12-10 Steffen Börm

Few-shot learning aims to transfer the knowledge acquired from training on a diverse set of tasks to unseen tasks from the same task distribution with a limited amount of labeled data. The underlying requirement for effective few-shot…

Machine Learning · Computer Science 2023-05-09 Shounak Datta , Sankha Subhra Mullick , Anish Chakrabarty , Swagatam Das

Existing video frame interpolation methods can only interpolate the frame at a given intermediate time-step, e.g. 1/2. In this paper, we aim to explore a more generalized kind of video frame interpolation, that at an arbitrary time-step. To…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Shixing Yu , Yiyang Ma , Wenhan Yang , Wei Xiang , Jiaying Liu

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…

Computer Vision and Pattern Recognition · Computer Science 2018-09-10 Tianyang Wang , Jun Huan , Bo Li

LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning. Though this success is often attributed to the Transformer architecture, our systematic…

Computation and Language · Computer Science 2024-10-25 Anna Mészáros , Szilvia Ujváry , Wieland Brendel , Patrik Reizinger , Ferenc Huszár

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

Large learning rates, when applied to gradient descent for nonconvex optimization, yield various implicit biases including the edge of stability (Cohen et al., 2021), balancing (Wang et al., 2022), and catapult (Lewkowycz et al., 2020).…

Machine Learning · Computer Science 2023-12-13 Yuqing Wang , Zhenghao Xu , Tuo Zhao , Molei Tao

We formally define algorithmic capture of combinatorial tasks as the ability of a transformer to extrapolate to arbitrary task sizes with controllable error and logarithmic sample adaptation, providing a sharp scaling criterion for…

Machine Learning · Computer Science 2026-05-08 Orit Davidovich , Zohar Ringel

Stable Diffusion (SD) has evolved DDPM (Denoising Diffusion Probabilistic Model) based image generation significantly by denoising in latent space instead of feature space. This popularized DDPM-based image generation as the cost and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Md Abu Obaida Zishan , Jannatun Noor , Annajiat Alim Rasel

Deep learning is a machine learning methodology using multi-layer neural network. A multi-layer neural network can be regarded as a chain of complete bipartite graphs. The nodes of the first partita is the input layer and the last is the…

Combinatorics · Mathematics 2020-05-11 Shoko Chisaki , Ryoh Fuji-Hara , Nobuko Miyamoto

Classical wisdom suggests that estimators should avoid fitting noise to achieve good generalization. In contrast, modern overparameterized models can yield small test error despite interpolating noise -- a phenomenon often called "benign…

Machine Learning · Statistics 2023-03-02 Michael Aerni , Marco Milanta , Konstantin Donhauser , Fanny Yang

Data augmentation by mixing samples, such as Mixup, has widely been used typically for classification tasks. However, this strategy is not always effective due to the gap between augmented samples for training and original samples for…

Machine Learning · Computer Science 2019-06-21 Takuya Shimada , Shoichiro Yamaguchi , Kohei Hayashi , Sosuke Kobayashi

Interpolation is an important property of classical and many non-classical logics that has been shown to have interesting applications in computer science and AI. Here we study the Interpolation Property for the the non-monotonic system of…

Logic in Computer Science · Computer Science 2014-01-17 Dov Gabbay , David Pearce , Agustín Valverde

With fast developments in computational power and algorithms, deep learning has made breakthroughs and been applied in many fields. However, generalization remains to be a critical challenge, and the limited generalization capability…

It is widely believed that complex machine learning models generally encode features through linear representations. This is the foundational hypothesis behind a vast body of work on interpretability. A key challenge toward extracting…

Machine Learning · Computer Science 2026-04-01 Allen Liu

Monte Carlo integration is a commonly used technique to compute intractable integrals and is typically thought to perform poorly for very high-dimensional integrals. To show that this is not always the case, we examine Monte Carlo…

Methodology · Statistics 2023-05-26 Yanbo Tang

Deep learning of the Artificial Neural Networks (ANN) can be treated as a particular class of interpolation problems. The goal is to find a neural network whose input-output map approximates well the desired map on a finite or an infinite…

Optimization and Control · Mathematics 2021-03-02 Andrei Agrachev , Andrey Sarychev