Negative Results for Active Learning with Convex Losses
نویسندگان
چکیده
We study the problem of active learning with convex loss functions. We prove that even under bounded noise constraints, the minimax rates for proper active learning are often no better than passive learning.
منابع مشابه
Active Learning as Non-Convex Optimization
We propose a new view of active learning algorithms as optimization. We show that many online active learning algorithms can be viewed as stochastic gradient descent on non-convex objective functions. Variations of some of these algorithms and objective functions have been previously proposed without noting this connection. We also point out a connection between the standard min-margin offline ...
متن کاملOnline Learning for Adversaries with Memory: Price of Past Mistakes
The framework of online learning with memory naturally captures learning problems with temporal effects, and was previously studied for the experts setting. In this work we extend the notion of learning with memory to the general Online Convex Optimization (OCO) framework, and present two algorithms that attain low regret. The first algorithm applies to Lipschitz continuous loss functions, obta...
متن کامل"On the (Non-)existence of Convex, Calibrated Surrogate Losses for Ranking"
We study surrogate losses for learning to rank, in a framework where the rankings are induced by scores and the task is to learn the scoring function. We focus on the calibration of surrogate losses with respect to a ranking evaluation metric, where the calibration is equivalent to the guarantee that near-optimal values of the surrogate risk imply near-optimal values of the risk defined by the ...
متن کاملOptimal Placement and Sizing of DGs and Shunt Capacitor Banks Simultaneously in Distribution Networks using Particle Swarm Optimization Algorithm Based on Adaptive Learning Strategy
Abstract: Optimization of DG and capacitors is a nonlinear objective optimization problem with equal and unequal constraints, and the efficiency of meta-heuristic methods for solving optimization problems has been proven to any degree of complex it. As the population grows and then electricity consumption increases, the need for generation increases, which further reduces voltage, increases los...
متن کاملConvex Calibration Dimension for Multiclass Loss Matrices
We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficien...
متن کامل