Ali Kavis
15 papers · 2018–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (20) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π€
Dynamic Duo
(13)
π§¬
Topic Evolution
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(75)
π₯
Unstoppable Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(14)
Optimization & Theory Β· Machine Learning
(13)
Mathematics & Optimization
(11)
Optimization
(11)
Artificial Intelligence
(5)
Deep Learning
(2)
Bayesian & Probabilistic
(2)
Core AI
(2)
Application Areas
(1)
Learning Paradigms
(1)
Optimization & Theory Β· Deep Learning
(1)
Techniques
(1)
Keywords
convergence rate
(5)
non-convex optimization
(4)
stochastic optimization
(3)
convex optimization
(3)
stochastic gradient descent
(2)
adaptive step size
(2)
constrained optimization
(1)
adversarial learning
(1)
langevin dynamics
(1)
accelerated optimization
(1)
latent dirichlet allocation
(1)
minimax optimization
(1)
adaptive learning rate
(1)
variance reduction
(1)
bayesian inference
(1)
mirror descent
(1)
dual averaging
(1)
stochastic convex optimization
(1)
oracle complexity
(1)
variational inequality
(1)
Papers
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
ICML 2025
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
NeurIPS 2024
Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
ICLR 2024
Universal Gradient Methods for Stochastic Convex Optimization
ICML 2024
Alternation makes the adversary weaker in two-player games
NeurIPS 2023
Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization
NeurIPS 2022
Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods
NeurIPS 2022
High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize
ICLR 2022
Sifting through the noise: Universal first-order methods for stochastic variational inequalities
NeurIPS 2021
STORM+: Fully Adaptive SGD with Recursive Momentum for Nonconvex Optimization
NeurIPS 2021
Double-Loop Unadjusted Langevin Algorithm
ICML 2020
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
NeurIPS 2020
Efficient learning of smooth probability functions from Bernoulli tests with guarantees
ICML 2019
UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
NeurIPS 2019
Mirrored Langevin Dynamics
NeurIPS 2018