English
Related papers

Related papers: The Implicit Bias of Gradient Descent on Separable…

200 papers

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tendency of the…

Machine Learning · Computer Science 2020-12-23 Assaf Dauber , Meir Feder , Tomer Koren , Roi Livni

The rising interest in pattern recognition and data analytics has spurred the development of innovative machine learning algorithms and tools. However, as each algorithm has its strengths and limitations, one is motivated to judiciously…

Machine Learning · Statistics 2018-07-31 Panagiotis A. Traganitis , Alba Pagès-Zamora , Georgios B. Giannakis

A deep equilibrium model uses implicit layers, which are implicitly defined through an equilibrium point of an infinite sequence of computation. It avoids any explicit computation of the infinite sequence by finding an equilibrium point…

Machine Learning · Computer Science 2021-02-19 Kenji Kawaguchi

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient…

Machine Learning · Computer Science 2025-10-27 Bhavya Vasudeva , Jung Whan Lee , Vatsal Sharan , Mahdi Soltanolkotabi

We initiate an investigation into the optimization properties of next-token prediction (NTP), the dominant training paradigm for modern language models. Specifically, we study the structural properties of the solutions selected by…

Machine Learning · Computer Science 2024-11-01 Christos Thrampoulidis

Cross-entropy loss is a common choice when it comes to multiclass classification tasks and language modeling in particular. Minimizing this loss results in language models of very good quality. We show that it is possible to fine-tune these…

Computation and Language · Computer Science 2019-01-16 Vadim Popov , Mikhail Kudinov

Real-world data is laden with outlying values. The challenge for machine learning is that the learner typically has no prior knowledge of whether the feedback it receives (losses, gradients, etc.) will be heavy-tailed or not. In this work,…

Machine Learning · Statistics 2020-12-16 Matthew J. Holland

The recent success of neural network models has shone light on a rather surprising statistical phenomenon: statistical models that perfectly fit noisy data can generalize well to unseen test data. Understanding this phenomenon of…

Machine Learning · Statistics 2022-09-13 Niladri S. Chatterji , Philip M. Long , Peter L. Bartlett

Recommender systems widely use implicit feedback such as click data because of its general availability. Although the presence of clicks signals the users' preference to some extent, the lack of such clicks does not necessarily indicate a…

Machine Learning · Statistics 2022-06-16 Yuta Saito , Suguru Yaginuma , Yuta Nishino , Hayato Sakata , Kazuhide Nakata

Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, prior work has shown promising results when using not only…

Machine Learning · Computer Science 2022-10-25 Kai Yan , Alexander G. Schwing , Yu-Xiong Wang

The widespread use of AI and ML models in sensitive areas raises significant concerns about fairness. While the research community has introduced various methods for bias mitigation in binary classification tasks, the issue remains…

Machine Learning · Computer Science 2026-03-24 Maryam Boubekraoui , Giordano d'Aloisio , Antinisca Di Marco

Overparameterized models may have many interpolating solutions; implicit regularization refers to the hidden preference of a particular optimization method towards a certain interpolating solution among the many. A by now established line…

Machine Learning · Computer Science 2024-09-18 Hung-Hsu Chou , Holger Rauhut , Rachel Ward

Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learned on the source task. But an initialization contains…

Machine Learning · Computer Science 2022-05-23 Ravid Shwartz-Ziv , Micah Goldblum , Hossein Souri , Sanyam Kapoor , Chen Zhu , Yann LeCun , Andrew Gordon Wilson

Learning models that can handle distribution shifts is a key challenge in domain generalization. Invariance learning, an approach that focuses on identifying features invariant across environments, improves model generalization by capturing…

Machine Learning · Statistics 2026-05-11 Yiran Jia , Jelena Bradic

Most deep learning research has focused on developing new model and training procedures. On the other hand the training objective has usually been restricted to combinations of standard losses. When the objective aligns well with the…

Machine Learning · Computer Science 2022-11-22 Shiv Shankar , Vihari Piratla

In the context of multivariate nonparametric regression with missing covariates, we propose Pattern Embedded Neural Networks (PENNs), which can be applied in conjunction with any existing imputation technique. In addition to a neural…

Methodology · Statistics 2025-04-30 Tianyi Ma , Tengyao Wang , Richard J. Samworth

Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for…

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

Computation and Language · Computer Science 2026-04-21 Jonathan Kamp , Roos Bakker , Dominique Blok

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…

Computation and Language · Computer Science 2019-09-11 Jiawei Wu , Wenhan Xiong , William Yang Wang

An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic…

Machine Learning · Computer Science 2026-01-21 Hong Zheng , Fei Teng