arXiv research

PCGS-TF uses a Transformer to adaptively control expert switching in non-stationary environments.

Study online learning in RKHS with dependent processes, focusing on \(β\)- and \(φ\)-mixing.

New algorithm uses imperfect advice to improve online bipartite matching performance.

New method tackles online DR-submodular maximization with improved regret guarantees.

SGD noise has no bias advantage in online learning, contrary to offline learning.

New algorithms reduce dynamic regret in online MDPs with changing losses.

Paper introduces a new $G^\star$ regret measure for online convex optimization with smooth losses.

How is popularity gained online? Is being successful strictly related to rapidly becoming viral in an online platform or is it possible to acquire popularity in a steady and disciplined fashion? What are other temporal characteristics that can unveil the popularity of online content? To answer these questions, we lever…

New algorithms reduce label collection for online prediction with expert advice.

Efficient algorithms find optimal monotone transforms for calibration under strictly convex losses.

Proposes methods for online conformal prediction with nested prediction sets across multiple confidence levels.

Study contextual online pricing with biased offline data, achieving optimal regret bounds.

We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm t…

SOOTT framework optimizes target tracking with robust and learning-augmented algorithms.

A new metric, Weighted Regret, unifies FDR and power evaluation in online multiple testing.

We present a framework and analysis of consistent binary classification for complex and non-decomposable performance metrics such as the F-measure and the Jaccard measure. The proposed framework is general, as it applies to both batch and online learning, and to both linear and non-linear models. Our work follows recen…

Study online control of unknown time-varying systems with negative and positive results.

ReLEX algorithm improves RL efficiency by selecting optimal representations.

A new mechanism reduces expert belief regret in online forecasting.

Improved dynamic regret analysis for strongly convex and smooth functions.

Study shows sample complexity for multicalibration is Θ(ε^-3) with polylogarithmic factors.

New RLHF framework handles general preference oracles without reward functions.

EML model tackles evolving features in online metric learning.

Study minimax-optimal rates for offline decision-making with function approximation.

Improving Bayesian filtering with strictly proper scoring rules

We consider the problem of unconstrained online convex optimization (OCO) with sub-exponential noise, a strictly more general problem than the standard OCO. In this setting, the learner receives a subgradient of the loss functions corrupted by sub-exponential noise and strives to achieve optimal regret guarantee, witho…

Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case performance, leading to suboptimal performance on easy instances, for example when there ex…

Improves decision tree performance by correcting split selection errors.

Improved algorithm reduces regret in corrupted expert advice setting.

In this paper, we show that if the tangent bundle of a smooth projective variety is strictly nef, then it is isomorphic to a projective space; if a projective variety $X^n$ $(n>4)$ has strictly nef $Λ^2 TX$, then it is isomorphic to $\mathbb{P}^n$ or quadric $\mathbb{Q}^n$. We also prove that on elliptic curves, strict…

Explains differences and similarities of strictly nef and ample vector bundles.

Two algorithms for linear contextual bandits with rare updates achieve optimal regret and efficiency.

The study shows how strictly convex domains in Euclidean spaces are rigid.

Defines new types of preinvex functions for optimization.

Proposes $φ$-balancing for more balanced expert utilization in MoE models.

In this work we propose Hebbian-descent as a biologically plausible learning rule for hetero-associative as well as auto-associative learning in single layer artificial neural networks. It can be used as a replacement for gradient descent as well as Hebbian learning, in particular in online learning, as it inherits the…

To survive in the dynamically-evolving world, we accumulate knowledge and improve our skills based on experience. In the process, gaining new knowledge does not disrupt our vigilance to external stimuli. In other words, our learning process is 'accumulative' and 'online' without interruption. However, despite the recen…

Study of strictly accretive matrices using Finsler geometry.

We introduce a new family of affine metrics on a locally strictly convex surface $M$ in affine 4-space. Then, we define the symmetric and antisymmetric equiaffine planes associated with each metric. We show that if $M$ is immersed in a locally strictly convex hyperquadric, then the symmetric and the antisymmetric plane…

In this paper, we study smooth complex projective varieties $X$ such that some exterior power $\bigwedge^r T_X$ of the tangent bundle is strictly nef. We prove that such varieties are rationally connected. We also classify the following two cases. If $T_X$ is strictly nef, then $X$ isomorphic to the projective space $\…

Improved convergence analysis for decentralized non-convex optimization.

Cooper and Long generalised Epstein and Penner's Euclidean cell decomposition of cusped hyperbolic manifolds of finite volume to non-compact strictly convex projective manifolds of finite volume. We show that Weeks' algorithm to compute this decomposition for a hyperbolic surface generalises to strictly convex projecti…

This paper extends a 3D result to higher dimensions for manifolds with positive curvature.

We obtain $C^2$ a priori estimates for solutions of the nonlinear second-order elliptic equation related to the geometric problem of finding a strictly locally convex hypersurface with prescribed curvature and boundary in a space form. Under the assumption of a strictly locally convex subsolution, we establish existenc…

This paper is devoted to $C^2$ a priori estimates for strictly locally convex radial graphs with prescribed Weingarten curvature and boundary in space forms. By constructing two-step continuity process and applying degree theory arguments, existence results in space forms are established for prescribed Gauss curvature …

New algorithm reduces online learning regret in uninformed Markov games.

This paper gives the first example of a unipotent group that is not virtually abelian and preserves a strictly convex domain.

The paper studies quasi-$X$-convex functions and their applications in optimization.