Zijian Liu
12 papers · 2022–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Cross-Pollinator (13) πΊοΈ Taxonomy Completionist (19) π Conference Polyglot (4) π§ Keyword Pioneer π Renaissance Researcher (6)
π
Interdisciplinary Bridge
π
Century Club
(11)
Conferences
ICML (6)
ICLR (3)
AAAI (1)
ALT (1)
COLT (1)
Top co-authors
Keywords
variance reduction
(2)
reinforcement learning
(1)
stochastic gradient descent
(1)
metric learning
(1)
robust optimization
(1)
semi-supervised learning
(1)
finite-sum optimization
(1)
non-convex optimization
(1)
convex optimization
(1)
pseudo labeling
(1)
robust reinforcement learning
(1)
speaker recognition
(1)
gradient descent
(1)
online convex optimization
(1)
distributionally robust
(1)
adaptive learning rate
(1)
accelerated gradient
(1)
distributionally robust optimization
(1)
regret bound
(1)
convergence rate
(1)
Papers
Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications
ALT 2026
Int*-Match: Balancing Intra-Class Compactness and Inter-Class Discrepancy for Semi-Supervised Speaker Recognition
AAAI 2025
Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
ICLR 2025
Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
ICML 2025
Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
ICLR 2024
On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity
ICML 2024
On the Last-Iterate Convergence of Shuffling Gradient Methods
ICML 2024
High Probability Convergence of Stochastic Gradient Methods
ICML 2023
On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
ICLR 2023
Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise
COLT 2023
Distributionally Robust $Q$-Learning
ICML 2022
Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction
ICML 2022