Turnitin
降AI改写
早检测系统
早降重系统
Turnitin-UK版
万方检测-期刊版
维普编辑部版
Grammarly检测
Paperpass检测
checkpass检测
PaperYY检测
[PDF][PDF] Online (multinomial) logistic bandit: Improved regret and constant computation cost
YJ Zhang, M Sugiyama - Advances in Neural Information …, 2024 - proceedings.neurips.cc
This paper investigates the logistic bandit problem, a variant of the generalized linear bandit
model that utilizes a logistic model to depict the feedback from an action. While most existing …
model that utilizes a logistic model to depict the feedback from an action. While most existing …
Adaptivity and non-stationarity: Problem-dependent dynamic regret for online convex optimization
We investigate online convex optimization in non-stationary environments and choose
dynamic regret as the performance measure, defined as the difference between cumulative …
dynamic regret as the performance measure, defined as the difference between cumulative …
Online composite optimization between stochastic and adversarial environments
We study online composite optimization under the Stochastically Extended Adversarial
(SEA) model. Specifically, each loss function consists of two parts: a fixed non-smooth and …
(SEA) model. Specifically, each loss function consists of two parts: a fixed non-smooth and …
Online conformal prediction with decaying step sizes
AN Angelopoulos, RF Barber, S Bates - arxiv preprint arxiv:2402.01139, 2024 - arxiv.org
We introduce a method for online conformal prediction with decaying step sizes. Like
previous methods, ours possesses a retrospective guarantee of coverage for arbitrary …
previous methods, ours possesses a retrospective guarantee of coverage for arbitrary …
Universal online learning with gradient variations: A multi-layer online ensemble approach
In this paper, we propose an online convex optimization approach with two different levels of
adaptivity. On a higher level, our approach is agnostic to the unknown types and curvatures …
adaptivity. On a higher level, our approach is agnostic to the unknown types and curvatures …
Byzantine-robust distributed online learning: Taming adversarial participants in an adversarial environment
This paper studies distributed online learning under Byzantine attacks. The performance of
an online learning algorithm is often characterized by (adversarial) regret, which evaluates …
an online learning algorithm is often characterized by (adversarial) regret, which evaluates …
Universal Online Convex Optimization with Projection per Round
To address the uncertainty in function types, recent progress in online convex optimization
(OCO) has spurred the development of universal algorithms that simultaneously attain …
(OCO) has spurred the development of universal algorithms that simultaneously attain …
Gradient-variation online learning under generalized smoothness
Gradient-variation online learning aims to achieve regret guarantees that scale with
variations in the gradients of online functions, which has been shown to be crucial for …
variations in the gradients of online functions, which has been shown to be crucial for …
Online optimization under randomly corrupted attacks
Existing algorithms in online optimization usually rely on trustful information, eg, reliable
knowledge of gradients, which makes them vulnerable to attacks. To take into account the …
knowledge of gradients, which makes them vulnerable to attacks. To take into account the …
Efficient non-stationary online learning by wavelets with applications to online distribution shift adaptation
YY Qian, P Zhao, YJ Zhang, M Sugiyama… - Forty-first International …, 2024 - openreview.net
Dynamic regret minimization offers a principled way for non-stationary online learning,
where the algorithm's performance is evaluated against changing comparators. Prevailing …
where the algorithm's performance is evaluated against changing comparators. Prevailing …