Search Results for author: Akshay Srinivasan

Found 4 papers, 1 papers with code

A Multilingual Evaluation of NER Robustness to Adversarial Inputs

no code implementations30 May 2023 Akshay Srinivasan, Sowmya Vajjala

Our results showed the NER models we explored across three languages (English, German and Hindi) are not very robust to such changes, as indicated by the fluctuations in the overall F1 score as well as in a more fine-grained evaluation.

named-entity-recognition Named Entity Recognition +1

MA-Dreamer: Coordination and communication through shared imagination

no code implementations10 Apr 2022 Kenzo Lobos-Tsunekawa, Akshay Srinivasan, Michael Spranger

Multi-agent RL is rendered difficult due to the non-stationary nature of environment perceived by individual agents.

How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy

1 code implementation14 Dec 2021 Badr AlKhamissi, Akshay Srinivasan, Zeb-Kurth Nelson, Sam Ritter

Alchemy is a new meta-learning environment rich enough to contain interesting abstractions, yet simple enough to make fine-grained analysis tractable.

Meta-Learning

Computing the Newton-step faster than Hessian accumulation

no code implementations2 Aug 2021 Akshay Srinivasan, Emanuel Todorov

In this paper, we show that given the computational graph of the function, this bound can be reduced to $O(m\tau^3)$, where $\tau, m$ are the width and size of a tree-decomposition of the graph.

Tree Decomposition

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