Oceania
Leveraged volume sampling for linear regression
Michal Derezinski, Manfred K. K. Warmuth, Daniel J. Hsu
Surprisingly we show that volume sampling can have poor behavior when we require a very accurate approximation - indeed worse than some i.i.d.
Differentially Private Uniformly Most Powerful Tests for Binomial Data
Jordan Awan, Aleksandra Slavkoviฤ
Outside the hypothesis testing setting, there is some work on optimal population inference under DP .
Sanity Checks for Saliency Maps
Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim
Through extensive experiments we show that some existing saliency methods are independent both of the model and of the data generating process.
Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks
Grant Rotskoff, Eric Vanden-Eijnden
The performance of neural networks on high-dimensional data distributions suggests that it may be possible to parameterize a representation of a given high-dimensional function with controllably small errors, potentially outperforming standard interpolation methods. We demonstrate, both theoretically and numerically, that this is indeed the case.
Alternating optimization of decision trees, with application to learning sparse oblique trees
Miguel A. Carreira-Perpinan, Pooya Tavallali
Neural Information Processing Systems http://nips.cc/
Neural Code Comprehension: A Learnable Representation of Code Semantics
Tal Ben-Nun, Alice Shoshana Jakobovits, Torsten Hoefler
Sifting through, categorizing, and understanding code thus becomes an essential task for a variety of fields.
A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication
Neural Information Processing Systems http://nips.cc/
Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters
Pavel Dvurechenskii, Darina Dvinskikh, Alexander Gasnikov, Cesar Uribe, Angelia Nedich
Given a basis space (e.g., pixel grid) and a transportation cost function (e.g.,
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator
Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang
Neural Information Processing Systems http://nips.cc/
The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
Constantinos Daskalakis, Ioannis Panageas
When they converge, do they converge to local min-max solutions? We characterize the limit points of two basic first order methods, namely Gradient Descent/Ascent (GDA) and Optimistic Gradient Descent Ascent (OGDA).