Active Learning with a Drifting Distribution
We study the problem of active learning in a stream-based setting, allowing the distribution of the examples to change over time. We prove upper bounds on the number of prediction mistakes and number of label requests for established disagreement-based active learning algorithms, both in the realizable case and under Tsybakov noise. We further prove minimax lower bounds for this problem.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningSimilar Papers 제목 키워드 기반
Kernel-Gradient Drifting Models
We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting models with directions induced by the kernel itself. Standard drifting is…
Generative Drifting for Conditional Medical Image Generation
Conditional medical image generation plays an important role in many clinically relevant imaging tasks. However, existing methods still face a fundamental challenge in balancing inference efficiency, patient-specific fid…
Medical Image GenerationMISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting
Multi-modal trajectory generation is essential for safe autonomous driving, yet existing diffusion-based planners suffer from high inference latency due to iterative neural function evaluations. This paper presents MISTY…
Autonomous DrivingMotion PlanningNonlinear Model Predictive Control for Enhanced Path Tracking and Autonomous Drifting through Direct Yaw Moment Control and Rear-Wheel-Steering
Path tracking (PT) controllers capable of replicating race driving techniques, such as drifting beyond the limits of handling, have the potential of enhancing active safety in critical conditions. This paper presents a n…
Model Predictive ControlSinkhorn-Drifting Generative Models
We establish a theoretical link between the recently proposed "drifting" generative dynamics and gradient flows induced by the Sinkhorn divergence. In a particle discretization, the drift field admits a cross-minus-self …