English
Related papers

Related papers: Tuning the Implicit Regularizer of Masked Diffusio…

200 papers

Grokking refers to delayed generalization in which the increase in test accuracy of a neural network occurs appreciably after the improvement in training accuracy This paper introduces several practical metrics including variance under…

Machine Learning · Computer Science 2025-07-17 Ahmed Salah , David Yevick

A key property of deep neural networks (DNNs) is their ability to learn new features during training. This intriguing aspect of deep learning stands out most clearly in recently reported Grokking phenomena. While mainly reflected as a…

Machine Learning · Statistics 2024-05-07 Noa Rubin , Inbar Seroussi , Zohar Ringel

In-context learning enables transformers to adapt to new tasks from a few examples at inference time, while grokking highlights that this generalization can emerge abruptly only after prolonged training. We study task generalization and…

Machine Learning · Statistics 2026-04-15 Abdessamed Qchohi , Simone Rossi

Regularization is a well studied problem in the context of neural networks. It is usually used to improve the generalization performance when the number of input samples is relatively small or heavily contaminated with noise. The…

Artificial Intelligence · Computer Science 2011-04-19 Salah Rifai , Xavier Glorot , Yoshua Bengio , Pascal Vincent

There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times. While there are some accounts of how these resources modulate statistical capacity, far…

Machine Learning · Computer Science 2023-01-18 Boaz Barak , Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Eran Malach , Cyril Zhang

Diffusion models have emerged as a powerful framework for generative modeling. At the heart of the methodology is score matching: learning gradients of families of log-densities for noisy versions of the data distribution at different…

Machine Learning · Computer Science 2025-03-19 Ricardo Baptista , Agnimitra Dasgupta , Nikola B. Kovachki , Assad Oberai , Andrew M. Stuart

In this paper, we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies. We introduce DVK, an imitation learning algorithm that…

Robotics · Computer Science 2025-03-12 Wei-Di Chang , Francois Hogan , Scott Fujimoto , David Meger , Gregory Dudek

Discrete diffusion models are often trained through clean-data prediction, but the prediction can be used in different ways to define the reverse dynamics. In Masked Diffusion Models (MDM) these choices largely coincide, whereas in Uniform…

Machine Learning · Computer Science 2026-05-22 Samson Gourevitch , Yazid Janati , Dario Shariatian , Umut Simsekli , Eric Moulines , Eric P. Xing , Alain Durmus

How diffusion models generalize beyond their training set is not known, and is somewhat mysterious given two facts: the optimum of the denoising score matching (DSM) objective usually used to train diffusion models is the score function of…

Machine Learning · Computer Science 2025-04-18 John J. Vastola

Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…

Computation and Language · Computer Science 2022-01-20 Yilin Yang , Akiko Eriguchi , Alexandre Muzio , Prasad Tadepalli , Stefan Lee , Hany Hassan

Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Zhendong Yang , Zhe Li , Mingqi Shao , Dachuan Shi , Zehuan Yuan , Chun Yuan

Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a challenge known as multimodal domain generalization (MMDG). Standard architectures employ…

Machine Learning · Computer Science 2026-05-05 Yavuz Yarici , Ghassan AlRegib

Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context.…

Artificial Intelligence · Computer Science 2026-05-28 Gokul Srinivasagan , Kai Hartung , Munir Georges

We introduce a training method for both better word representation and performance, which we call GROVER (Gradual Rumination On the Vector with maskERs). The method is to gradually and iteratively add random noises to word embeddings while…

Machine Learning · Computer Science 2019-11-12 Hwiyeol Jo , Byoung-Tak Zhang

Gradient descent (GD) is crucial for generalization in machine learning models, as it induces implicit regularization, promoting compact representations. In this work, we examine the role of GD in inducing implicit regularization for tensor…

Optimization and Control · Mathematics 2023-10-25 Ziye Ma , Javad Lavaei , Somayeh Sojoudi

In this work we study generalization guarantees for the metric learning problem, where the metric is induced by a neural network type embedding of the data. Specifically, we provide uniform generalization bounds for two regimes -- the…

Machine Learning · Computer Science 2021-02-09 Mark Kozdoba , Shie Mannor

This paper proposes a new regularization algorithm referred to as macro-block dropout. The overfitting issue has been a difficult problem in training large neural network models. The dropout technique has proven to be simple yet very…

Machine Learning · Computer Science 2023-01-02 Chanwoo Kim , Sathish Indurti , Jinhwan Park , Wonyong Sung

Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations. MLM trains a model to predict a random sample of input tokens that have been replaced…

Computation and Language · Computer Science 2021-09-07 Atsuki Yamaguchi , George Chrysostomou , Katerina Margatina , Nikolaos Aletras

Finetuning vision foundation models often improves in-domain accuracy but comes at the cost of robustness under distribution shift. We revisit Mixout, a stochastic regularizer that intermittently replaces finetuned weights with their…

Machine Learning · Computer Science 2025-10-09 Masih Aminbeidokhti , Heitor Rapela Medeiros , Eric Granger , Marco Pedersoli

Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. To compensate for the over-parameterized models, numerous regularization techniques have been introduced such as those based on dropout.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Mateusz Michalkiewicz , Masoud Faraki , Xiang Yu , Manmohan Chandraker , Mahsa Baktashmotlagh