182 citations · 274 across the 12 of their papers we have counts for
19 papers
HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression
Jiaqi Gu, Ben Keller, Jean Kossaifi +3
Transformers have attained superior performance in natural language processing and computer vision. Their self-attention and feedforward layers are overparameterized, limiting infe…
Towards a scalable discrete quantum generative adversarial neural network
Smit Chaudhary, Patrick Huembeli, Ian MacCormack +3
We introduce a fully quantum generative adversarial network intended for use with binary data. The architecture incorporates several features found in other classical and quantum m…
Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
Anuj Mahajan, Mikayel Samvelyan, Lei Mao +6
We present an extended abstract for the previously published work TESSERACT [Mahajan et al., 2021], which proposes a novel solution for Reinforcement Learning (RL) in large, factor…
Defensive Tensorization
Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya +5
We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as…
Tensor Methods in Computer Vision and Deep Learning
Yannis Panagakis, Jean Kossaifi, Grigorios G. Chrysos +4
Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions. Inherently able to efficiently capture structured, latent…
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Anuj Mahajan, Mikayel Samvelyan, Lei Mao +6
Reinforcement Learning in large action spaces is a challenging problem. Cooperative multi-agent reinforcement learning (MARL) exacerbates matters by imposing various constraints on…