English
Related papers

Related papers: Model Merging is Secretly Certifiable: Non-Vacuous…

200 papers

This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By training on…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Zhaodi Zhang , Zhiyi Xue , Yang Chen , Si Liu , Yueling Zhang , Jing Liu , Min Zhang

The flexibility of decision boundaries in neural networks that are unguided by training data is a well-known problem typically resolved with generalization methods. A surprising result from recent knowledge distillation (KD) literature is…

Machine Learning · Computer Science 2024-10-28 HeeSeung Jung , Kangil Kim , Hoyong Kim , Jong-Hun Shin

Deep neural networks suffer from poor generalization to unseen environments when the underlying data distribution is different from that in the training set. By learning minimum sufficient representations from training data, the information…

Machine Learning · Computer Science 2021-10-13 Francesco Alesiani , Shujian Yu , Xi Yu

With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature…

Machine Learning · Computer Science 2019-01-08 Tsui-Wei Weng , Pin-Yu Chen , Lam M. Nguyen , Mark S. Squillante , Ivan Oseledets , Luca Daniel

Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate…

Computer Vision and Pattern Recognition · Computer Science 2024-02-20 Xuelun Shen , Zhipeng Cai , Wei Yin , Matthias Müller , Zijun Li , Kaixuan Wang , Xiaozhi Chen , Cheng Wang

Machine learning models are vulnerable to adversarial attacks. One approach to addressing this vulnerability is certification, which focuses on models that are guaranteed to be robust for a given perturbation size. A drawback of recent…

Machine Learning · Computer Science 2020-10-07 Ryan Campbell , Chris Finlay , Adam M Oberman

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Machine Learning · Computer Science 2020-11-03 Aditi Raghunathan , Jacob Steinhardt , Percy Liang

This paper provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the…

Machine Learning · Statistics 2023-08-29 Kenji Kawaguchi , Leslie Pack Kaelbling , Yoshua Bengio

Federated Learning (FL) has surged in prominence due to its capability of collaborative model training without direct data sharing. However, the vast disparity in local data distributions among clients, often termed the Non-Independent…

Machine Learning · Computer Science 2024-12-12 Zheshun Wu , Zenglin Xu , Dun Zeng , Qifan Wang , Jie Liu

Over the past decade, machine learning has demonstrated impressive results, often surpassing human capabilities in sensing tasks relevant to autonomous flight. Unlike traditional aerospace software, the parameters of machine learning models…

Machine Learning · Computer Science 2023-10-06 Jean-Guillaume Durand , Arthur Dubois , Robert J. Moss

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the…

Machine Learning · Computer Science 2017-02-28 Chiyuan Zhang , Samy Bengio , Moritz Hardt , Benjamin Recht , Oriol Vinyals

Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. Recently, leveraging the supervised or semi-unsupervised learning paradigms, which benefits…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Suncheng Xiang , Hao Chen , Wei Ran , Zefang Yu , Ting Liu , Dahong Qian , Yuzhuo Fu

Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous for large models at…

Machine Learning · Statistics 2024-07-26 Sanae Lotfi , Yilun Kuang , Brandon Amos , Micah Goldblum , Marc Finzi , Andrew Gordon Wilson

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. However, prior approaches face generalization limitations from two…

Computation and Language · Computer Science 2026-05-28 Quanen Sun , Changxin Tian , Ke Shi , Cai Chen , Cunyin Peng , Jia Liu , Kunlong Chen , Zhiqiang Zhang

This paper explores the generalization characteristics of iterative learning algorithms with bounded updates for non-convex loss functions, employing information-theoretic techniques. Our key contribution is a novel bound for the…

Machine Learning · Computer Science 2023-10-17 Jingwen Fu , Nanning Zheng

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

Machine Learning · Statistics 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz

Training deep networks requires various design decisions regarding for instance their architecture, data augmentation, or optimization. In this work, we find these training variations to result in networks learning unique feature sets from…

Machine Learning · Computer Science 2024-02-27 Karsten Roth , Lukas Thede , Almut Sophia Koepke , Oriol Vinyals , Olivier Hénaff , Zeynep Akata

Generalization remains a central yet unresolved challenge in deep learning, particularly the ability to predict a model's performance beyond its training distribution using quantities available prior to test-time evaluation. Building on the…

Neural sequence models trained with maximum likelihood estimation have led to breakthroughs in many tasks, where success is defined by the gap between training and test performance. However, their ability to achieve stronger forms of…

Machine Learning · Computer Science 2022-02-25 Sean Welleck , Peter West , Jize Cao , Yejin Choi

Machine learning technologies have been used in a wide range of practical systems. In practical situations, it is natural to expect the input-output pairs of a machine learning model to satisfy some requirements. However, it is difficult to…

Machine Learning · Computer Science 2022-10-12 Masaaki Nishino , Kengo Nakamura , Norihito Yasuda