Good Papers

Showing papers from University of Toronto Vector Institute Show all papers

80%Must read
?Must readVote to see the score
NeurIPS 2026U Toronto Vector InstituteU Hong KongU TorontoOptimization

Adaptively Incorporating Directional Hints into Zeroth-Order Optimization

CV-ZOD adaptively integrates directional hints into zeroth-order optimization, achieving rates that interpolate between first- and zeroth-order convergence based on hint quality without prior knowledge.

Alexander Ryabchenko, Jian Qian, Wenlong Mou

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 2/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U Toronto Vector InstituteU Illinois at ChicagoU of Toronto; VectorLearning theory

Capacity-Constrained Online Convex Optimization with Delayed Feedback

Capacity-constrained online convex optimization with delayed feedback achieves near-standard regret with logarithmic tracking capacity via randomized scheduling and weighted FTRL.

Alexander Ryabchenko, Idan Attias, Dan Roy

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it
lenient 2/5
medium 6/10
strict 1/5
72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U Toronto Vector InstituteU Illinois at ChicagoU of Toronto; VectorOptimization

A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees

A reduction framework converts online convex optimization with delayed feedback into immediate feedback, improving delay-dependent regret bounds for both first-order and bandit settings via continuous-time decomposition.

Alexander Ryabchenko, Idan Attias, Dan Roy

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 8 of 20 reviewers recommend it
lenient 2/5
medium 4/10
strict 2/5