A Challenge in Reweighting Data with Bilevel Optimization
In many scenarios, one uses a large training set to train a model with the goal of performing well on a smaller testing set with a different distribution. Learning a weight for each data point of the training set is an appealing solution, as it ideally allows one to automatically learn the importance of each training point for generalization on the testing set. This task is usually formalized as a bilevel optimization problem. Classical bilevel solvers are based on a warm-start strategy where both the parameters of the models and the data weights are learned at the same time. We show that this joint dynamic may lead to sub-optimal solutions, for which the final data weights are very sparse. This finding illustrates the difficulty of data reweighting and offers a clue as to why this method is rarely used in practice.
Code (0)
등록된 구현이 없습니다.
Tasks
Bilevel OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting
Bilevel optimization has shown its utility across various machine learning settings, yet most algorithms in practice require second-order information, making it challenging to scale them up. Only recently, a paradigm of …
Bilevel OptimizationInstruction FollowingMathUnlocking Global Optimality in Bilevel Optimization: A Pilot Study
Bilevel optimization has witnessed a resurgence of interest, driven by its critical role in trustworthy and efficient AI applications. While many recent works have established convergence to stationary points or local mi…
Bilevel OptimizationRepresentation LearningBROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
Stochastic bilevel optimization (SBO) has become a standard framework for hyperparameter learning, data reweighting, representation learning, and data-mixture optimization in deep learning. Existing exact single-loop SBO…
Representation LearningBilevel OptimizationStability and Generalization of Bilevel Programming in Hyperparameter Optimization
The (gradient-based) bilevel programming framework is widely used in hyperparameter optimization and has achieved excellent performance empirically. Previous theoretical work mainly focuses on its optimization properties…
Hyperparameter OptimizationCommunication-Efficient Robust Federated Learning with Noisy Labels
Federated learning (FL) is a promising privacy-preserving machine learning paradigm over distributed located data. In FL, the data is kept locally by each user. This protects the user privacy, but also makes the server d…
Bilevel OptimizationFederated LearningLearning with noisy labelsPrivacy Preserving