Search Results for author: Nishant Mehta

Found 4 papers, 0 papers with code

Safe-Bayesian Generalized Linear Regression

no code implementations21 Oct 2019 Rianne de Heide, Alisa Kirichenko, Nishant Mehta, Peter Grünwald

We study generalized Bayesian inference under misspecification, i. e. when the model is 'wrong but useful'.

Bayesian Inference regression

Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models

no code implementations WS 2018 Avery Hiebert, Cole Peterson, Alona Fyshe, Nishant Mehta

While Long Short-Term Memory networks (LSTMs) and other forms of recurrent neural network have been successfully applied to language modeling on a character level, the hidden state dynamics of these models can be difficult to interpret.

Clustering Language Modelling +1

Generalized Mixability via Entropic Duality

no code implementations24 Jun 2014 Mark D. Reid, Rafael M. Frongillo, Robert C. Williamson, Nishant Mehta

Mixability is a property of a loss which characterizes when fast convergence is possible in the game of prediction with expert advice.

Minimax Multi-Task Learning and a Generalized Loss-Compositional Paradigm for MTL

no code implementations NeurIPS 2012 Nishant Mehta, Dongryeol Lee, Alexander G. Gray

We show theoretically that minimax MTL tends to avoid worst case outcomes on newly drawn test tasks in the learning to learn (LTL) test setting.

Multi-Task Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.