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
77.36/100
前 1.6%
全站排名 #1,061
发表论文11 篇
平均评分
年均产出5.5 篇/年
Lenka Zdeborova
研究方向
theory of artificial neural networks · matrix factorization · compressed sensing · statistical inference · Bayesian inference · phase transitions · statistical physics · message passing algorithms
23
The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets
NeurIPS 2025Spotlight
三作18
Bayes optimal learning of attention-indexed models
NeurIPS 2025Poster
通讯20
Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
NeurIPS 2025Poster
三作23
Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
NeurIPS 2025Poster
通讯16
The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
NeurIPS 2025Poster
三作10
Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
ICML 2025Poster
三作17
Counting in small transformers: The delicate interplay between attention and feed-forward layers
ICLR 2025Rejected
三作10
Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
ICML 2025Poster
通讯11
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
NeurIPS 2024Spotlight
通讯14
Bayes-optimal learning of an extensive-width neural network from quadratically many samples
NeurIPS 2024Poster
通讯14
Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
ICLR 2024Poster
通讯