English
Related papers

Related papers: Inside-Out: Measuring Generalization in Vision Tra…

200 papers

Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on adversarial attacks…

Machine Learning · Computer Science 2023-07-07 Julia Lust , Alexandru P. Condurache

Modern regression problems often involve high-dimensional data and a careful tuning of the regularization hyperparameters is crucial to avoid overly complex models that may overfit the training data while guaranteeing desirable properties…

Machine Learning · Computer Science 2026-04-08 Maria-Florina Balcan , Saumya Goyal , Dravyansh Sharma

The diffusion probabilistic generative models are widely used to generate high-quality data. Though they can synthetic data that does not exist in the training set, the rationale behind such generalization is still unexplored. In this…

Machine Learning · Computer Science 2023-05-25 Mingyang Yi , Jiacheng Sun , Zhenguo Li

Domain Generalization (DG) aims to learn models whose performance remains high on unseen domains encountered at test-time by using data from multiple related source domains. Many existing DG algorithms reduce the divergence between source…

Machine Learning · Computer Science 2022-06-27 Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Jihun Hamm

Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many…

Machine Learning · Computer Science 2019-09-18 Xiaotong Liu , Hong Xuan , Zeyu Zhang , Abby Stylianou , Robert Pless

Testing practices within the machine learning (ML) community have centered around assessing a learned model's predictive performance measured against a test dataset, often drawn from the same distribution as the training dataset. While…

Machine Learning · Computer Science 2021-12-07 Negar Rostamzadeh , Ben Hutchinson , Christina Greer , Vinodkumar Prabhakaran

Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem…

Machine Learning · Computer Science 2021-04-16 Haoran Zhang , Natalie Dullerud , Laleh Seyyed-Kalantari , Quaid Morris , Shalmali Joshi , Marzyeh Ghassemi

The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by measuring necessity and sufficiency. We measure circuit reuse, the proportion of…

Computation and Language · Computer Science 2026-05-12 Michael Li , Nishant Subramani

Deep Neural Networks (DNNs) achieve state-of-the-art performance on numerous applications. However, it is difficult to tell beforehand if a DNN receiving an input will deliver the correct output since their decision criteria are usually…

Machine Learning · Computer Science 2021-09-07 Julia Lust , Alexandru Paul Condurache

Motion prediction, recently popularized as world models, refers to the anticipation of future agent states or scene evolution, which is rooted in human cognition, bridging perception and decision-making. It enables intelligent systems, such…

Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific…

Machine Learning · Computer Science 2024-07-12 Joseph Miller , Bilal Chughtai , William Saunders

This study examines the generalization ability of algorithm performance prediction models across various benchmark suites. Comparing the statistical similarity between the problem collections with the accuracy of performance prediction…

Machine Learning · Computer Science 2024-05-22 Ana Nikolikj , Ana Kostovska , Gjorgjina Cenikj , Carola Doerr , Tome Eftimov

Despite the recent advances showing that a model pre-trained on large-scale source code data is able to gain appreciable generalization capability, it still requires a sizeable amount of data on the target task for fine-tuning. And the…

Software Engineering · Computer Science 2023-02-13 Changan Niu , Chuanyi Li , Vincent Ng , Bin Luo

During the inversion of discrete linear systems noise in data can be amplified and result in meaningless solutions. To combat this effect, characteristics of solutions that are considered desirable are mathematically implemented during…

Numerical Analysis · Mathematics 2023-02-07 Michael J. Byrne , Rosemary A. Renaut

Trained with a sufficiently large training and testing dataset, Deep Neural Networks (DNNs) are expected to generalize. However, inputs may deviate from the training dataset distribution in real deployments. This is a fundamental issue with…

Machine Learning · Computer Science 2021-10-07 Yan Xiao , Yun Lin , Ivan Beschastnikh , Changsheng Sun , David S. Rosenblum , Jin Song Dong

Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less studied for indoor single-image depth prediction. We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset…

Computer Vision and Pattern Recognition · Computer Science 2024-01-31 Cho-Ying Wu , Yiqi Zhong , Junying Wang , Ulrich Neumann

The task of distribution generalization concerns making reliable prediction of a response in unseen environments. The structural causal models are shown to be useful to model distribution changes through intervention. Motivated by the…

Methodology · Statistics 2022-06-14 Kang Du , Yu Xiang

Deep tabular modelling increasingly relies on in-context learning where, during inference, a model receives a set of $(x,y)$ pairs as context and predicts labels for new inputs without weight updates. We challenge the prevailing view that…

Machine Learning · Computer Science 2025-11-14 Junwei Ma , Nour Shaheen , Alex Labach , Amine Mhedhbi , Frank Hutter , Anthony L. Caterini , Valentin Thomas

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

Existing website fingerprinting and traffic classification solutions do not work well when the evaluation context changes, as their performances often heavily rely on context-specific assumptions. To clarify this problem, we take three…

Networking and Internet Architecture · Computer Science 2025-07-10 Elham Akbari , Zihao Zhou , Mohammad Ali Salahuddin , Noura Limam , Raouf Boutaba , Bertrand Mathieu , Stephanie Moteau , Stephane Tuffin