English
Related papers

Related papers: Generalization vs. Memorization in Autoregressive …

200 papers

The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown that when training and sampling are performed perfectly,…

Machine Learning · Statistics 2025-07-08 Tyler Farghly , Patrick Rebeschini , George Deligiannidis , Arnaud Doucet

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Nishant Jain , Harkirat Behl , Yogesh Singh Rawat , Vibhav Vineet

This paper proposes a technique for training a neural network by minimizing a surrogate loss that approximates the target evaluation metric, which may be non-differentiable. The surrogate is learned via a deep embedding where the Euclidean…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Yash Patel , Tomas Hodan , Jiri Matas

Neural surrogates for partial differential equations (PDEs) have become popular due to their potential to quickly simulate physics. With a few exceptions, neural surrogates generally treat the forward evolution of time-dependent PDEs as a…

Machine Learning · Computer Science 2025-04-18 Anthony Zhou , Amir Barati Farimani

Deep learning models frequently exploit spurious features in training data to achieve low training error, often resulting in poor generalization when faced with shifted testing distributions. To address this issue, various methods from…

Machine Learning · Computer Science 2025-02-11 Geraldin Nanfack , Eugene Belilovsky

We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to…

Machine Learning · Computer Science 2020-07-09 Yujia Li , Felix Gimeno , Pushmeet Kohli , Oriol Vinyals

Deep learning models have a propensity for fitting the entire training set even with random labels, which requires memorization of every training sample. In this paper, we explore the memorization effect in adversarial training (AT) for…

Machine Learning · Computer Science 2022-03-15 Yinpeng Dong , Ke Xu , Xiao Yang , Tianyu Pang , Zhijie Deng , Hang Su , Jun Zhu

Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of…

Machine Learning · Computer Science 2022-05-19 Akihito Yoshii , Susumu Tokumoto , Fuyuki Ishikawa

A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that…

Artificial Intelligence · Computer Science 2026-04-09 Qihan Ren , Peng Wang , Ruikun Cai , Shuai Shao , Dadi Guo , Yuejin Xie , Yafu Li , Quanshi Zhang , Xia Hu , Jing Shao , Dongrui Liu

Modeling the evolution of physical systems is critical to many applications in science and engineering. As the evolution of these systems is governed by partial differential equations (PDEs), there are a number of computational simulations…

Machine Learning · Computer Science 2025-03-17 Bharat Srikishan , Daniel O'Malley , Mohamed Mehana , Nicholas Lubbers , Nikhil Muralidhar

Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task and (ii) intuitively appealing modular models that require background knowledge to be…

Computation and Language · Computer Science 2019-04-23 Dzmitry Bahdanau , Shikhar Murty , Michael Noukhovitch , Thien Huu Nguyen , Harm de Vries , Aaron Courville

Recent advancements in DeepFake generation, along with the proliferation of open-source tools, have significantly lowered the barrier for creating synthetic media. This trend poses a serious threat to the integrity and authenticity of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Spiros Baxavanakis , Manos Schinas , Symeon Papadopoulos

The notion of generalization has moved away from the classical one defined in statistical learning theory towards an emphasis on out-of-domain generalization (OODG). There has been a growing focus on generalization from easy to hard, where…

Machine Learning · Computer Science 2025-06-23 Yingshan Chang , Yonatan Bisk

In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the train and test distributions. Such models are often…

Machine Learning · Computer Science 2021-11-23 Anshul Nasery , Soumyadeep Thakur , Vihari Piratla , Abir De , Sunita Sarawagi

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high…

Machine Learning · Computer Science 2018-05-03 Ludwig Schmidt , Shibani Santurkar , Dimitris Tsipras , Kunal Talwar , Aleksander Mądry

Despite the extreme popularity of deep learning in science and industry, its formal understanding is limited. This thesis puts forth notions of rank as key for developing a theory of deep learning, focusing on the fundamental aspects of…

Machine Learning · Computer Science 2024-12-31 Noam Razin

Deep reinforcement-learning methods have achieved remarkable performance on challenging control tasks. Observations of the resulting behavior give the impression that the agent has constructed a generalized representation that supports…

Machine Learning · Computer Science 2018-12-12 Sam Witty , Jun Ki Lee , Emma Tosch , Akanksha Atrey , Michael Littman , David Jensen

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

Machine Learning · Computer Science 2020-02-26 Satrajit Chatterjee

Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using hand-crafted auxiliary tasks and pseudo rewards. Automatically learning such representations in an…

Machine Learning · Computer Science 2023-06-28 Somjit Nath , Gopeshh Raaj Subbaraj , Khimya Khetarpal , Samira Ebrahimi Kahou

Deep Gaussian processes (DGPs) are increasingly popular as predictive models in machine learning (ML) for their non-stationary flexibility and ability to cope with abrupt regime changes in training data. Here we explore DGPs as surrogates…

Methodology · Statistics 2021-08-27 Annie Sauer , Robert B. Gramacy , David Higdon