Frederic Koehler
where else to find them
what they talk about
where they keep going back
no series more than once — all 4 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Unexpected Test Losses from Generalization Theory? | Emerging Generalization Settings 2024 | 2024-09-09 |
Shows that overfitting can change the effective test loss: empirical L1 training behaves like a Huber and then a squared loss as capacity grows, and a ReLU… | ||
| Preconditioning In Sparse Linear Regression Using Graphical Structure | Algorithmic Aspects of Causal Inference 2022 | 2022-03-18 |
Shows a concrete claim: when covariates form a low treewidth Gaussian graphical model there is an explicit change-of-basis (a preconditioner) that preserves… | ||
| Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting | Deep Learning Theory Symposium 2021 | 2021-12-03 |
Proves a uniform‑convergence bound for interpolators in Gaussian linear regression: test loss ≤ (Gaussian‑width(K))^2 / n up to small additive/multiplicative… | ||
| On the Power of Preconditioning in Sparse Linear Regression | Meet the Fellows Welcome Event | 2021-09-08 |
Proves that using the precision-matrix graph and a nested dissection preconditioner lets Lasso attain the information-theoretic Mahalanobis error rate when the… | ||
| nothing matches | ||