Profiles2020-2025
Meisam Razaviyayn
University of Southern California
9Papers
5Last author
18Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers9
- PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient ConflictsAuthor 4 of 5NeurIPS 2025 · 8 citations
- DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise ReductionAuthor 5 of 6ICLR 2025
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and GeneralizationAuthor 2 of 3ICLR 2024 · 33 citations
- f-FERM: A Scalable Framework for Robust Fair Empirical Risk MinimizationAuthor 3 of 3ICLR 2024 · 4 citations
- Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex LossesAuthor 2 of 2ICLR 2023 · 2 citations
- Stochastic Differentially Private and Fair LearningAuthor 3 of 3ICLR 2023 · 1 citation
- A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron AttributionsAuthor 3 of 3ICML 2022 · 85 citations
- Rényi Fair InferenceAuthor 4 of 4ICLR 2020 · 69 citations
- Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization ProblemsAuthor 2 of 5NeurIPS 2020 · 19 citations
