Nati Srebro
where else to find them
what they talk about
where they keep going back
no series more than once — all 5 in the filters
on a stage with
- JM Landsbergonce
- Jim Demmelonce
- Kirk Pruhsonce
all 5 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Computational Thinking on Learning Models | The Role of TCS in Modern Machine Learning | 2026-05-26 |
Argues that autoregressive chain-of-thought is the right computational model because a simple next-token function H iterated T times decouples runtime from… | ||
| Program Presentations | Eleventh Annual Industry Day | 2025-11-13 |
Three concrete takeaways: kilobyte zkSNARK proofs let a cellphone verify a year‑long computation in under a second and power rollups; multi‑party computation… | ||
| Overview of Statistical Learning Theory Part 2 | Modern Paradigms in Generalization Boot Camp 2024 | 2024-08-27 |
Surveys classical tools and then ties them to optimization: uniform convergence via fat-shattering dimension and Rademacher complexity gives sample bounds… | ||
| Overview of Statistical Learning Theory Part 1 | Modern Paradigms in Generalization Boot Camp 2024 | 2024-08-27 |
Survey of classical statistical learning theory that pins down learnability: VC dimension and Sauer's Lemma give tight sample complexity and explain the sharp… | ||
| Tutorial: Implicit Bias I | Deep Learning Theory Workshop and Summer School 2022 | 2022-08-01 |
Claims that classic statistical learning tools largely apply to deep learning while implicit bias and benign overfitting need refined views; uses Rademacher… | ||
| Tutorial: Implicit Bias II | Deep Learning Theory Workshop and Summer School 2022 | 2022-08-01 |
Experiments fit MNIST nets with 8,16,64,512,1000+ hidden units and show zero training error on random labels (Zhang et al.), yet test error keeps falling… | ||
| Implicit Regularization I | Deep Learning Boot Camp 2019 | 2019-05-28 |
Overparameterized nets and matrix completion have many global minima, yet the chosen optimizer determines which beach the solution lands on: SGD vs Adam… | ||
| Implicit Regularization II | Deep Learning Boot Camp 2019 | 2019-05-28 |
Claims that optimization selects specific solutions: for underdetermined least squares gradient descent from zero yields the minimum norm solution; for… | ||
| nothing matches | ||