Binghui Peng
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 3 in the filters
on a stage with
- Allen Liuonce
- Aviad Rubinsteinonce
- Jan van den Brandonce
all 7 in the filters
who talks about the same things
- Jan van den Brand2 talks
- Omri Weinstein4 talks
- Zhao Song2 talks
- Ke Wang11 talks
- Yu Wang16 talks
- Linzhang Wang6 talks
| title | conference | date |
|---|---|---|
| Theoretical understanding of learning through the computational lens | Meet the Fellows Welcome Event Fall 2024 | 2024-09-03 |
Proves that worst-case continual learning requires memory scales linearly with number of tasks but shows allowing multiple passes over the task stream removes… | ||
| Memory-Regret Tradeoff for Online Learning | Sketching and Algorithm Design 2023 | 2023-10-09 |
Shows two concrete tradeoffs and gives matching algorithms and lower bounds: against an oblivious adversary an algorithm using S bits achieves about sqrt(nT/S)… | ||
| Training (Overparametrized) Neural Networks in Near-Linear Time | ITCS 2021 | 2021-01-06 |
Proves that training two‑layer ReLU networks with width m and n samples runs in near‑linear time by replacing the costly J J^T computation (previously Ω(m… | ||
| Distributed load balancing: a new framework and improved guarantees | ITCS 2021 | 2021-01-06 |
Distributed algorithm balances loads on a bipartite source–worker graph in the CONGEST model, producing a 1+ε approximation for general convex objectives by… | ||
| nothing matches | ||