On-Demand Sampling: Learning Optimally from Multiple DistributionsAuthors are ordered alphabetically. Correspondence to eric.zh@berkeley.edu.
This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions.
On-Demand Sampling: Learning Optimally from Multiple DistributionsAuthors are ordered alphabetically. Correspondence to eric.zh@berkeley.edu. On-Demand Sampling: Learning Optimally from Multiple Distributions † † thanks: Authors are ordered alphabetically. Correspondence to eric.zh@berkeley.edu . Nika Haghtalab Michael I. Jordan Eric Zhao Abstract Social and real-world considerations such as robustness, fairness, social welfare and multi-agent tradeoffs have given rise to multi-distribution learning paradigms, such as collaborative [ 9 ] , group distributionally robust [ 50 ] , and fair federa
Explore this link on the map →related reading
- Competing with sampling — Alignment Research Centeralignment.org
- IsoCompute Playbook: Optimally Scaling Sampling Compute for RL Training of LLMscompute-optimal-rl-llm-scaling.github.io
- arxiv.org/pdf/2511.08544arxiv.org
- ARC progress update: Competing with sampling — LessWronglesswrong.com
- [1911.08731] Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationarxiv.org
- [1909.02060] Distributionally Robust Language Modelingarxiv.org
- Bryon Aragam // University of Chicagobryonaragam.com
- deeplearningbook.org/contents/ml.htmldeeplearningbook.org
- Gregory Gundersengregorygundersen.com
- [1511.03643] Unifying distillation and privileged informationarxiv.org
- Paperscseweb.ucsd.edu
- [2406.04219] Multi-Agent Imitation Learning: Value is Easy, Regret is Hardarxiv.org