English
Related papers

Related papers: Tracing the Path to Grokking: Embeddings, Dropout,…

200 papers

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

Dropout is a simple but efficient regularization technique for achieving better generalization of deep neural networks (DNNs); hence it is widely used in tasks based on DNNs. During training, dropout randomly discards a portion of the…

Neural and Evolutionary Computing · Computer Science 2020-10-22 Hiroshi Inoue

We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representative reasoning types, composition and comparison, we…

Computation and Language · Computer Science 2024-11-01 Boshi Wang , Xiang Yue , Yu Su , Huan Sun

Transformer-based language models are widely deployed for reasoning, yet their behavior under inference-time stochasticity remains underexplored. While dropout is common during training, its inference-time effects via Monte Carlo sampling…

Machine Learning · Computer Science 2026-03-19 Antônio Junior Alves Caiado , Michael Hahsler

We propose a combinatorial and graph-theoretic theory of dropout by modeling training as a random walk over a high-dimensional graph of binary subnetworks. Each node represents a masked version of the network, and dropout induces stochastic…

Machine Learning · Computer Science 2025-05-30 Sahil Rajesh Dhayalkar

We study the dynamics of gradient flow with small weight decay on general training losses $F: \mathbb{R}^d \to \mathbb{R}$. Under mild regularity assumptions and assuming convergence of the unregularised gradient flow, we show that the…

Machine Learning · Computer Science 2025-11-06 Etienne Boursier , Scott Pesme , Radu-Alexandru Dragomir

We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task. Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training…

Machine Learning · Computer Science 2026-02-20 Jianliang He , Leda Wang , Siyu Chen , Zhuoran Yang

While Large Language Models (LLMs) excel at factual retrieval, they often struggle with the "curse of two-hop reasoning" in compositional tasks. Recent research suggests that parameter-sharing transformers can bridge this gap by forming a…

Computation and Language · Computer Science 2026-01-15 Kaiyu He , Zhang Mian , Peilin Wu , Xinya Du , Zhiyu Chen

Neural networks readily learn a subset of the modular arithmetic tasks, while failing to generalize on the rest. This limitation remains unmoved by the choice of architecture and training strategies. On the other hand, an analytical…

Machine Learning · Computer Science 2024-06-06 Darshil Doshi , Tianyu He , Aritra Das , Andrey Gromov

We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context--a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-augmented generation…

Computation and Language · Computer Science 2025-02-07 Ang Lv , Ruobing Xie , Xingwu Sun , Zhanhui Kang , Rui Yan

Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior. Empirically, this regime often yields improved…

Machine Learning · Computer Science 2026-04-22 Mario Tuci , Caner Korkmaz , Umut Şimşekli , Tolga Birdal

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the…

Machine Learning · Computer Science 2023-11-01 Jingwen Fu , Zhizheng Zhang , Dacheng Yin , Yan Lu , Nanning Zheng

Dropout Regularization, serving to reduce variance, is nearly ubiquitous in Deep Learning models. We explore the relationship between the dropout rate and model complexity by training 2,000 neural networks configured with random…

Machine Learning · Computer Science 2021-08-30 Christopher Sun , Jai Sharma , Milind Maiti

Increasing the L2 regularization of Deep Neural Networks (DNNs) causes a first-order phase transition into the under-parametrized phase -- the so-called onset-of learning. We explain this transition via the scalar (Ricci) curvature of the…

Machine Learning · Computer Science 2025-08-29 Ibrahim Talha Ersoy , Karoline Wiesner

Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detectors. Current explanations of dropout include bagging, naive…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Tongliang Liu , Fang Xu , Dacheng Tao

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

Training a deep neural network (DNN) often involves stochastic optimization, which means each run will produce a different model. Several works suggest this variability is negligible when models have the same performance, which in the case…

Machine Learning · Statistics 2023-10-03 Sinjini Banerjee , Reilly Cannon , Tim Marrinan , Tony Chiang , Anand D. Sarwate

Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks…

Machine Learning · Computer Science 2021-12-20 Yu-Lin Tsai , Chia-Yi Hsu , Chia-Mu Yu , Pin-Yu Chen

Deep neural networks have become the default choice for many of the machine learning tasks such as classification and regression. Dropout, a method commonly used to improve the convergence of deep neural networks, generates an ensemble of…

Machine Learning · Statistics 2019-04-11 Tal Kachman , Michal Moshkovitz , Michal Rosen-Zvi

We explore the critical data size in language models, a threshold that marks a fundamental shift from quick memorization to slow generalization. We formalize the phase transition under the grokking configuration into the Data Efficiency…

Computation and Language · Computer Science 2024-05-24 Xuekai Zhu , Yao Fu , Bowen Zhou , Zhouhan Lin
‹ Prev 1 4 5 6 7 8 10 Next ›