Zobrazeno 1 - 10
of 145
pro vyhledávání: '"Hanneke, Steve"'
We consider the problem of multiclass transductive online learning when the number of labels can be unbounded. Previous works by Ben-David et al. [1997] and Hanneke et al. [2023b] only consider the case of binary and finite label spaces, respectively
Externí odkaz:
http://arxiv.org/abs/2411.01634
We present novel reductions from sample compression schemes in multiclass classification, regression, and adversarially robust learning settings to binary sample compression schemes. Assuming we have a compression scheme for binary classes of size $f
Externí odkaz:
http://arxiv.org/abs/2410.13012
Autor:
Hanneke, Steve, Wang, Kun
We study the stochastic noisy bandit problem with an unknown reward function $f^*$ in a known function class $\mathcal{F}$. Formally, a model $M$ maps arms $\pi$ to a probability distribution $M(\pi)$ of reward. A model class $\mathcal{M}$ is a colle
Externí odkaz:
http://arxiv.org/abs/2410.09597
Autor:
Hanneke, Steve, Kpotufe, Samory
We show that some basic moduli of continuity $\delta$ -- which measure how fast target risk decreases as source risk decreases -- appear to be at the root of many of the classical relatedness measures in transfer learning and related literature. Name
Externí odkaz:
http://arxiv.org/abs/2408.16189
PAC learning, dating back to Valiant'84 and Vapnik and Chervonenkis'64,'74, is a classic model for studying supervised learning. In the agnostic setting, we have access to a hypothesis set $\mathcal{H}$ and a training set of labeled samples $(x_1,y_1
Externí odkaz:
http://arxiv.org/abs/2407.19777
This work continues to investigate the link between differentially private (DP) and online learning. Alon, Livni, Malliaris, and Moran (2019) showed that for binary concept classes, DP learnability of a given class implies that it has a finite Little
Externí odkaz:
http://arxiv.org/abs/2407.07765
This work studies embedding of arbitrary VC classes in well-behaved VC classes, focusing particularly on extremal classes. Our main result expresses an impossibility: such embeddings necessarily require a significant increase in dimension. In particu
Externí odkaz:
http://arxiv.org/abs/2405.17120
List learning is a variant of supervised classification where the learner outputs multiple plausible labels for each instance rather than just one. We investigate classical principles related to generalization within the context of list learning. Our
Externí odkaz:
http://arxiv.org/abs/2403.10889
Autor:
Devulapalli, Pramith, Hanneke, Steve
Understanding the self-directed learning complexity has been an important problem that has captured the attention of the online learning theory community since the early 1990s. Within this framework, the learner is allowed to adaptively choose its ne
Externí odkaz:
http://arxiv.org/abs/2402.13400
Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the loss compared to an oblivious
Externí odkaz:
http://arxiv.org/abs/2402.07453