Aleksandr Beznosikov

~Aleksandr_Beznosikov1

论文总数

8.0

年均投稿

5.2

平均评分

接收情况3/16

会议分布

ICLR

ICML

NeurIPS

发表论文 (16 篇)

202513 篇

5.0

Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation

ICLR 2025withdrawn

5.2

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

ICLR 2025Rejected

4.9

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

ICML 2025Poster

Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity

NeurIPS 2025Rejected

4.9

Sign Operator for Coping with Heavy-Tailed Noise: High Probability Convergence Bounds with Extensions to Distributed Optimization and Comparison Oracle

ICML 2025Rejected

3.0

Broadening Discovery through Structural Models: Multimodal Combination of Local and Structural Properties for Predicting Chemical Features.

ICLR 2025withdrawn

4.8

Label Privacy in Split Learning for Large Models with Parameter-Efficient Training

ICLR 2025Rejected

7.8

A Robust Training Method for Federated Learning with Partial Participation

NeurIPS 2025Rejected

20243 篇

5.7

Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting

ICLR 2024Poster

5.3

Label Privacy in Split Learning for Large Models with Parameter-Efficient Training

NeurIPS 2024Rejected

3.5

Privacy Preserving API Fine-tuning for LLMs

ICLR 2024Rejected

合作者 (20)

Alexander Gasnikov7 篇

Aleksandr Beznosikov

发表论文 (16 篇)

202513 篇

Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

Adaptive Regularized Newton Methods with Inexact Hessian

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

Decentralized Finite-Sum Optimization over Time-Varying Networks

Clipping Improves Adam and AdaGrad when the Noise Is Heavy-Tailed

Markovian Compression: Looking to the Past Helps Accelerate the Future

Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity

Sign Operator for Coping with Heavy-Tailed Noise: High Probability Convergence Bounds with Extensions to Distributed Optimization and Comparison Oracle

Broadening Discovery through Structural Models: Multimodal Combination of Local and Structural Properties for Predicting Chemical Features.

Label Privacy in Split Learning for Large Models with Parameter-Efficient Training

A Robust Training Method for Federated Learning with Partial Participation

20243 篇

Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting

Label Privacy in Split Learning for Large Models with Parameter-Efficient Training

Privacy Preserving API Fine-tuning for LLMs