paper-with-me

홈 › Papers

STEER : Simple Temporal Regularization For Neural ODE

2020-12-01 · NeurIPS 2020 12 · Arnab Ghosh, Harkirat Behl, Emilien Dupont, Philip Torr, Vinay Namboodiri

Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. Recent works have shown that regularizing the dynamics of the ODE can partially alleviate this. In this paper we propose a new regularization technique: randomly sampling the end time of the ODE during training. The proposed regularization is simple to implement, has negligible overhead and is effective across a wide variety of tasks. Further, the technique is orthogonal to several other methods proposed to regularize the dynamics of ODEs and as such can be used in conjunction with them. We show through experiments on normalizing flows, time series models and image recognition that the proposed regularization can significantly decrease training time and even improve performance over baseline models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

STEER: Simple Temporal Regularization For Neural ODEs

2020-06-18 · Arnab Ghosh, Harkirat Singh Behl, Emilien Dupont, Philip H. S. Torr 외

Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. R…

Time SeriesTime Series Analysis

Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos

2025-04-21 · Songping Wang, Hanqing Liu, Yueming Lyu, Xiantao Hu 외

Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. Firs…

Adversarial RobustnessVideo Recognition

Steering Information Utility in Key-Value Memory for Language Model Post-Training

2025-07-07 · Chunyuan Deng, Ruidi Chang, Hanjie Chen arxiv

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of kn…

Temporal Regularization in Markov Decision Process

2018-11-01 · Pierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to re…

Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Temporal Regularization for Markov Decision Process

2018-12-01 · NeurIPS 2018 12 · Pierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to re…

Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)