影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
63.55/100
前 3.9%
全站排名 #2,480
发表论文13 篇
平均评分
年均产出4.3 篇/年
Robert M. Gower
研究方向
adaptive gradient methods; · learning rate schedules · Policy Gradient methods; · stochastic optimization; variance reduced methods; stochastic gradient descent; quasi-Newton methods; second order methods · numerical linear algebra; sketching
18
The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon Algorithm
ICLR 2026Oral
通讯16
Non-Euclidian Gradient Descent Occurs at the Edge of Stability
ICLR 2026Rejected
通讯11
Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation
ICLR 2026Rejected
一作14
An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
ICLR 2026Rejected
通讯5
Schedulers for Schedule-free: Theoretically inspired hyperparameters
ICLR 2026Withdrawn
三作18
In Search of Adam’s Secret Sauce
NeurIPS 2025Oral
二作22
Fisher meets Feynman: score-based variational inference with a product of experts
NeurIPS 2025Spotlight
二作32
SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms
ICLR 2025Rejected
13
Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation
ICML 2025Rejected
一作