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
70.03/100
前 2.6%
全站排名 #1,700
发表论文16 篇
平均评分
年均产出5.3 篇/年
Aurelien Lucchi
研究方向
Reasoning · Fine-tuning · Stochastic Optimization · Convex Optimization · Non-convex Optimization · Deep Learning theory
20
Optimizer Choice Matters For The Emergence of Neural Collapse
ICLR 2026Poster
通讯14
Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective
ICLR 2026Poster
12
Why Do We Need Warm-up? A Theoretical Perspective
ICLR 2026Rejected
三作17
When Bias Meets Trainability: Connecting Theories of Initialization
ICLR 2026Poster
三作14
Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy
ICLR 2026Rejected
三作16
On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach
ICLR 2026Rejected
4
Unpacking Softmax: How Logits Norm Drives Representation Collapse, Compression and Generalization
ICLR 2026Withdrawn
22
Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
ICLR 2025Poster
通讯21
Enhancing Optimizer Stability: Momentum Adaptation of NGN Step-size
ICLR 2025Rejected
通讯23
Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
NeurIPS 2025Poster
通讯7
Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy
ICLR 2025Rejected
三作