Industry
Learning What and Where to Draw
Scott E. Reed, Zeynep Akata, Santosh Mohan, Samuel Tenka, Bernt Schiele, Honglak Lee
Neural Information Processing Systems http://nips.cc/
Concentration of Multilinear Functions of the Ising Model with Applications to Network Data
Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath
Neural Information Processing Systems http://nips.cc/
Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data
Stรฉphanie ALLASSONNIERE, Juliette Chevallier, Stephane Oudard
Neural Information Processing Systems http://nips.cc/
Equality of Opportunity in Supervised Learning
Moritz Hardt, Eric Price, Eric Price, Nati Srebro
We enourage readers to consult the more complete manuscript on the arXiv.
Cortical microcircuits as gated-recurrent neural networks
Rui Costa, Ioannis Alexandros Assael, Brendan Shillingford, Nando de Freitas, TIm Vogels
Our empirical evaluation across sequential image classification and language modelling tasks shows that subLSTM units can achieve similar performance to LSTM units.
Hindsight Experience Replay
Marcin Andrychowicz, Dwight Crow, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, OpenAI Pieter Abbeel, Wojciech Zaremba
We demonstrate our approach on the task of manipulating objects with a robotic arm.
Accelerating Stochastic Composition Optimization
Mengdi Wang, Ji Liu, Ethan Fang
The popular stochastic gradient methods are well suited for minimizing expected-value objective functions or the sum of a large number of loss functions. Stochastic gradient methods find wide applications in estimation, online learning, and training of deep neural networks.
An Error Detection and Correction Framework for Connectomics
Jonathan Zung, Ignacio Tartavull, Kisuk Lee, H. Sebastian Seung
Both tasks take as input the raw image and a binary mask representing a candidate object.
Local Aggregative Games
In contrast, in a game theoretic setting, myopic strategic interactions among players lead to a Nash equilibrium or locally optimal configuration rather than highest scoring global configuration.
Structured Sparse Regression via Greedy Hard Thresholding
Prateek Jain, Nikhil Rao, Inderjit S. Dhillon
In this paper, we show that such NP-hard projections can not only be avoided by appealing to submodular optimization, but such methods come with strong theoretical guarantees even in the presence of poorly conditioned data (i.e. say when two features have