Research

• Variance Reduction Can Improve Trade-off In Multi-Objective Learning

  • Heshan Fernando, Lisha Chen, Songtao Lu, Pin-Yu Chen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Gaowen Liu, Meng Wang, Tianyi Chen

• Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

  • Lisha Chen*, Heshan Fernando*, Yiming Ying, Tianyi Chen

• Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach

  • Heshan Fernnado, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen

• On the Stability Analysis of Open Federated Learning Systems

  • Youbang Sun, Heshan Fernando, Tianyi Chen, Shahin Shahrampour

Preprints

• Mitigating Forgetting in LLM Supervised Fine-tuning and Preference Learning

  • Heshan Fernando, Han Shen, Parikshit Ram, Yi Zhou, Horst Samulowitz, Nathalie Baracaldo, Tianyi Chen