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
27.29/100
前 27.7%
全站排名 #17,853
发表论文11 篇
平均评分
年均产出3.7 篇/年
Philip Zmushko
研究方向
Quantization Aware Training · Optimization · Optimizers for LLM · LLM Quantization · Vertical Federated Learning · Privacy
20
Sign-SGD via Parameter-Free Optimization
ICLR 2026Poster
7
CompSGD: Robust Comparison-Based Approach for Zeroth-Order Optimization under $(L_0, L_1)$-Smoothness and Heavy-Tailed Noise
ICLR 2026Rejected
二作6
Power of Sign: High Probability Bounds Under $(L_0, L_1)$-smoothness and Heavy-Tailed Noise
ICLR 2026Rejected
二作5
Just a Simple Transformation is Enough for Data Protection in Split Learning
ICLR 2026Withdrawn
二作6
Supra-Tuning: Combining Outlier and Low-Rank Adaptation for Sparse and Efficient LLM Fine-Tuning
ICLR 2026Rejected
二作33
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
ICLR 2025Rejected
一作12
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
ICML 2025Poster
一作11
Sign Operator for Coping with Heavy-Tailed Noise: High Probability Convergence Bounds with Extensions to Distributed Optimization and Comparison Oracle
ICML 2025Rejected
二作22
Label Privacy in Split Learning for Large Models with Parameter-Efficient Training
ICLR 2025Rejected
一作