no code implementations • 17 Jan 2023 • John Duchi, Saminul Haque, Rohith Kuditipudi
We design an $(\varepsilon, \delta)$-differentially private algorithm to estimate the mean of a $d$-variate distribution, with unknown covariance $\Sigma$, that is adaptive to $\Sigma$.
1 code implementation • 26 May 2022 • Niladri S. Chatterji, Saminul Haque, Tatsunori Hashimoto
While a broad range of techniques have been proposed to tackle distribution shift, the simple baseline of training on an $\textit{undersampled}$ balanced dataset often achieves close to state-of-the-art-accuracy across several popular benchmarks.
1 code implementation • ICLR 2022 • Ke Alexander Wang, Niladri S. Chatterji, Saminul Haque, Tatsunori Hashimoto
As a remedy, we show that polynomially-tailed losses restore the effects of importance reweighting in correcting distribution shift in overparameterized models.
1 code implementation • NeurIPS 2019 • Qiyang Li, Saminul Haque, Cem Anil, James Lucas, Roger Grosse, Jörn-Henrik Jacobsen
Our BCOP parameterization allows us to train large convolutional networks with provable Lipschitz bounds.