output
20072025
most citedLearning how to explain neural networks: PatternNet and PatternAttribution

290 citations

Showing 2018Show all

11 papers · 1 filter

cs.DS2018

Secretary Ranking with Minimal Inversions

Sepehr Assadi, Eric Balkanski, Renato Paes Leme

We study a twist on the classic secretary problem, which we term the secretary ranking problem: elements from an ordered set arrive in random order and instead of picking the maxim…

cs.LG2018★ 20 cited

Kernel Exponential Family Estimation via Doubly Dual Embedding

Bo Dai, Hanjun Dai, Arthur Gretton +3

We investigate penalized maximum log-likelihood estimation for exponential family distributions whose natural parameter resides in a reproducing kernel Hilbert space. Key to our ap…

cs.LG2018★ 178 cited

MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare

Edward Choi, Cao Xiao, Walter F. Stewart +1

Deep learning models exhibit state-of-the-art performance for many predictive healthcare tasks using electronic health records (EHR) data, but these models typically require traini…

cs.DS2018★ 1 cited

Multitasking Capacity: Hardness Results and Improved Constructions

Noga Alon, Jonathan D. Cohen, Thomas L. Griffiths +5

We consider the problem of determining the maximal such that every matching of size (or at most ) in a bipartite graph contains an induced matching of s…

cs.MA2018★ 2 cited

Pommerman: A Multi-Agent Playground

Cinjon Resnick, Wes Eldridge, David Ha +5

We present Pommerman, a multi-agent environment based on the classic console game Bomberman. Pommerman consists of a set of scenarios, each having at least four players and contain…

hep-th2018★ 17 cited

Upper and Lower Bounds on the Integrated Null Energy in Gravity

Stefan Leichenauer, Adam Levine

We prove a lower bound on the integrated null energy along achronal geodesic segments using induced gravity on a brane in AdS/CFT. The bound follows from the assumption that bulk c…