Stable Learning

Stable learning in machine learning focuses on developing algorithms and models that maintain consistent performance across various data distributions and training conditions, mitigating issues like catastrophic forgetting and overfitting. Current research emphasizes techniques like regularization (e.g., KL regularization, Wasserstein proximals), improved gradient descent methods (e.g., trapezoidal gradient descent), and attention mechanisms to enhance robustness and generalization in diverse settings, including reinforcement learning, federated learning, and domain adaptation. These advancements are crucial for building reliable and dependable AI systems, particularly in safety-critical applications and scenarios with data heterogeneity or distribution shifts.

Papers

November 14, 2024

FxTS-Net: Fixed-Time Stable Learning Framework for Neural ODEs
Chaoyang Luo, Yan Zou, Wanying Li, Nanjing Huang
Neural ODE Neural Ordinary Differential Equation Lyapunov Function Stable Learning Prescribed Time

October 30, 2024

Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints
Jay Bear, Adam Prügel-Bennett, Jonathon Hare
Practical Algorithm Participation Constraint Recurrent Network Deep Understanding Intermediate Representation Iterative Algorithm Lipschitz Operator Stable Learning Lipschitz Constraint

October 28, 2024

Scaling-based Data Augmentation for Generative Models and its Theoretical Extension
Yoshitaka Koike, Takumi Nakagawa, Hiroki Waida, Takafumi Kanamori
Generative Model Data Augmentation GAN Model Stable Learning Diffusion GAN Natural Extension

August 26, 2024

Focused Large Language Models are Stable Many-Shot Learners
Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li
Large Language Model Context Learning Training Free Task Adaptation Stable Learning

June 19, 2024

Trapezoidal Gradient Descent for Effective Reinforcement Learning in Spiking Networks
Yuhao Pan, Xiucheng Wang, Nan Cheng, Qi Qiu
Reinforcement Learning Gradient Descent Spiking Neural Network Gradient Approximation Stable Learning Effective Reinforcement Learning

May 22, 2024

Learning heavy-tailed distributions with Wasserstein-proximal-regularized $\alpha$-divergences
Ziyu Chen, Hyemin Gu, Markos A. Katsoulakis, Luc Rey-Bellet, Wei Zhu
Heavy Tailed Stable Learning Beta Divergence Wasserstein 2

April 21, 2024

Training-Conditional Coverage Bounds for Uniformly Stable Learning Algorithms
Mehrdad Pournaderi, Yu Xiang
Conformal Prediction Stable Learning Conditional Coverage Conformal Prediction Region

March 1, 2024

Stability-Certified Learning of Control Systems with Quadratic Nonlinearities
Igor Pontes Duff, Pawan Goyal, Peter Benner
Dynamical System Nonlinear Model Input to State Stable Learning Control System Operator Inference Low Dimensional

February 6, 2024

DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
Yair Schiff, Zhong Yi Wan, Jeffrey B. Parker, Stephan Hoyer, Volodymyr Kuleshov, Fei Sha, Leonardo Zepeda-Núñez
Learning Dynamic Chaotic System Learned Dynamic Lyapunov Exponent Stable Learning Invariant Set

November 2, 2023

Local Borsuk-Ulam, Stability, and Replicability
Zachary Chase, Bogdan Chornomaz, Shay Moran, Amir Yehudayoff
Core Stability List Replicability Stable Learning Class Disjoint Data Global Similarity

October 2, 2023

Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning
Debora Caldarola, Barbara Caputo, Marco Ciccone
Strong Generalization Heterogeneous Federated Learning Stable Learning Model Averaging Concrete Aggregate

August 19, 2023

StROL: Stabilized and Robust Online Learning from Humans
Shaunak A. Mehta, Forrest Meng, Andrea Bajcsy, Dylan P. Losey
Real Human Robust Learning Learning Dynamic Stable Learning Reward Function Parameter

July 26, 2023

Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
Aamal Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras
Early Stage Convergence Core Stability Multi Agent Learning Zero Sum Game Two Player Stable Learning Convergence Behavior

July 24, 2023

SL: Stable Learning in Source-Free Domain Adaption for Medical Image Segmentation
Yixin Chen, Yan Wang
Domain Adaptation Medical Image Segmentation Unsupervised Domain Adaptation Domain Shift Source Free Domain Adaptation Stable Learning

June 25, 2023

Mining Stable Preferences: Adaptive Modality Decorrelation for Multimedia Recommendation
Jinghao Zhang, Qiang Liu, Shu Wu, Liang Wang
Multi Modality Stable Learning Asset Correlation Individual Preference Stability Multimedia Recommendation

June 16, 2023

SLACK: Stable Learning of Augmentations with Cold-start and KL regularization
Juliette Marrie, Michael Arbel, Diane Larlus, Julien Mairal
Data Augmentation Soft Augmentation Cold Start Stable Learning Augmentation Policy Kullback Leibler Data Augmentation Algorithm

February 27, 2023

Taylor TD-learning
Michele Garibbo, Maxime Robeyns, Laurence Aitchison
Linear Function Approximation Stable Learning Continuous Action

January 20, 2023

Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning
Zifan Wu, Chao Yu, Chen Chen, Jianye Hao, Hankz Hankui Zhuo
Model Based Reinforcement Learning Policy Learning Predictive Uncertainty High Level Plan Model Learning Stable Learning

December 2, 2022

Stable Learning via Sparse Variable Independence
Han Yu, Peng Cui, Yue He, Zheyan Shen, Yong Lin, Renzhe Xu, Xingxuan Zhang
Stable Learning Sample Reweighting Covariate Shift Generalization

July 14, 2022

Improving Multi-Interest Network with Stable Learning
Zhaocheng Liu, Yingtao Luo, Di Zeng, Qiang Liu, Daqing Chang, Dongying Kong, Zhi Chen
Modern Recommender System Stable Learning Interest Network Multi Interest