no code implementations • 20 Jan 2023 • Colin White, Mahmoud Safari, Rhea Sukthanker, Binxin Ru, Thomas Elsken, Arber Zela, Debadeepta Dey, Frank Hutter
Specialized, high-performing neural architectures are crucial to the success of deep learning in these areas.
Natural Language Understanding Neural Architecture Search +2
1 code implementation • 17 Oct 2022 • Yuhong Li, Tianle Cai, Yi Zhang, Deming Chen, Debadeepta Dey
We focus on the structure of the convolution kernel and identify two critical but intuitive principles enjoyed by S4 that are sufficient to make up an effective global convolutional model: 1) The parameterization of the convolutional kernel needs to be efficient in the sense that the number of parameters should scale sub-linearly with sequence length.
Ranked #6 on Long-range modeling on LRA
no code implementations • 6 Oct 2022 • Ganesh Jawahar, Subhabrata Mukherjee, Debadeepta Dey, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Caio Cesar Teodoro Mendes, Gustavo Henrique de Rosa, Shital Shah
In this work, we study the more challenging open-domain setting consisting of low frequency user prompt patterns (or broad prompts, e. g., prompt about 93rd academy awards) and demonstrate the effectiveness of character-based language models.
no code implementations • 15 Mar 2022 • Sharath Girish, Debadeepta Dey, Neel Joshi, Vibhav Vineet, Shital Shah, Caio Cesar Teodoro Mendes, Abhinav Shrivastava, Yale Song
We conduct a large-scale study with over 100 variants of ResNet and MobileNet architectures and evaluate them across 11 downstream scenarios in the SSL setting.
1 code implementation • 4 Mar 2022 • Mojan Javaheripi, Gustavo H. de Rosa, Subhabrata Mukherjee, Shital Shah, Tomasz L. Religa, Caio C. T. Mendes, Sebastien Bubeck, Farinaz Koushanfar, Debadeepta Dey
Results show that the perplexity of 16-layer GPT-2 and Transformer-XL can be achieved with up to 1. 5x, 2. 5x faster runtime and 1. 2x, 2. 0x lower peak memory utilization.
no code implementations • 29 Jan 2022 • Dongkuan Xu, Subhabrata Mukherjee, Xiaodong Liu, Debadeepta Dey, Wenhui Wang, Xiang Zhang, Ahmed Hassan Awadallah, Jianfeng Gao
Our framework AutoDistil addresses above challenges with the following steps: (a) Incorporates inductive bias and heuristics to partition Transformer search space into K compact sub-spaces (K=3 for typical student sizes of base, small and tiny); (b) Trains one SuperLM for each sub-space using task-agnostic objective (e. g., self-attention distillation) with weight-sharing of students; (c) Lightweight search for the optimal student without re-training.
no code implementations • 29 Sep 2021 • Debadeepta Dey, Shital Shah, Sebastien Bubeck
We propose a simple but powerful method which we call FEAR, for ranking architectures in any search space.
1 code implementation • 7 Jun 2021 • Debadeepta Dey, Shital Shah, Sebastien Bubeck
We propose a simple but powerful method which we call FEAR, for ranking architectures in any search space.
no code implementations • ICML Workshop AutoML 2021 • Debadeepta Dey, Shital Shah, Sebastien Bubeck
By training different architectures in the search space to the same training or validation error and subsequently comparing the usefulness of the features extracted on the task-dataset of interest by freezing most of the architecture we obtain quick estimates of the relative performance.
1 code implementation • 2020 Conference on Robot Learning 2020 • Florian Achermann, Andrey Kolobov, Debadeepta Dey, Timo Hinzmann, Jen Jen Chung, Roland Siegwart, Nicholas Lawrance
This model is then deployed for fast and accurate online interest point detection.
no code implementations • 18 Jun 2020 • Dilip Arumugam, Debadeepta Dey, Alekh Agarwal, Asli Celikyilmaz, Elnaz Nouri, Bill Dolan
While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, where trajectories \textit{only} contain expert observations, have not been met with the same success.
1 code implementation • ACL 2020 • Angela S. Lin, Sudha Rao, Asli Celikyilmaz, Elnaz Nouri, Chris Brockett, Debadeepta Dey, Bill Dolan
Learning to align these different instruction sets is challenging because: a) different recipes vary in their order of instructions and use of ingredients; and b) video instructions can be noisy and tend to contain far more information than text instructions.
2 code implementations • NeurIPS 2019 • Hanzhang Hu, John Langford, Rich Caruana, Saurajit Mukherjee, Eric Horvitz, Debadeepta Dey
We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers.
no code implementations • 12 May 2019 • Aditya Modi, Debadeepta Dey, Alekh Agarwal, Adith Swaminathan, Besmira Nushi, Sean Andrist, Eric Horvitz
We address the opportunity to maximize the utility of an overall computing system by employing reinforcement learning to guide the configuration of the set of interacting modules that comprise the system.
1 code implementation • CVPR 2019 • Khanh Nguyen, Debadeepta Dey, Chris Brockett, Bill Dolan
We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments.
no code implementations • 27 Sep 2018 • Felix Berkenkamp, Debadeepta Dey, Ashish Kapoor
Deep reinforcement learning has enabled robots to complete complex tasks in simulation.
no code implementations • ECCV 2018 • Benjamin Hepp, Debadeepta Dey, Sudipta N. Sinha, Ashish Kapoor, Neel Joshi, Otmar Hilliges
We propose to learn a better utility function that predicts the usefulness of future viewpoints.
no code implementations • 23 May 2018 • Ramya Ramakrishnan, Ece Kamar, Debadeepta Dey, Julie Shah, Eric Horvitz
Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments.
no code implementations • ICLR 2018 • Hanzhang Hu, Debadeepta Dey, Martial Hebert, J. Andrew Bagnell
We present an approach for anytime predictions in deep neural networks (DNNs).
1 code implementation • ICLR 2018 • Hanzhang Hu, Debadeepta Dey, Allison Del Giorno, Martial Hebert, J. Andrew Bagnell
Skip connections are increasingly utilized by deep neural networks to improve accuracy and cost-efficiency.
no code implementations • 22 Aug 2017 • Hanzhang Hu, Debadeepta Dey, Martial Hebert, J. Andrew Bagnell
Experimentally, the adaptive weights induce more competitive anytime predictions on multiple recognition data-sets and models than non-adaptive approaches including weighing all losses equally.
no code implementations • ICML 2017 • Wen Sun, Debadeepta Dey, Ashish Kapoor
To address this problem, we first study online convex programming in the full information setting where in each round the learner receives an adversarial convex loss and a convex constraint.
25 code implementations • 15 May 2017 • Shital Shah, Debadeepta Dey, Chris Lovett, Ashish Kapoor
Developing and testing algorithms for autonomous vehicles in real world is an expensive and time consuming process.
no code implementations • ICCV 2017 • Mike Roberts, Debadeepta Dey, Anh Truong, Sudipta Sinha, Shital Shah, Ashish Kapoor, Pat Hanrahan, Neel Joshi
Drones equipped with cameras are emerging as a powerful tool for large-scale aerial 3D scanning, but existing automatic flight planners do not exploit all available information about the scene, and can therefore produce inaccurate and incomplete 3D models.
no code implementations • CVPR 2017 • Artem Rozantsev, Sudipta N. Sinha, Debadeepta Dey, Pascal Fua
Our main contribution is a new bundle adjustment procedure which in addition to optimizing the camera poses, regularizes the point trajectory using a prior based on motion dynamics (or specifically flight dynamics).
no code implementations • 13 Nov 2016 • Sanjiban Choudhury, Ashish Kapoor, Gireeja Ranade, Debadeepta Dey
The budgeted information gathering problem - where a robot with a fixed fuel budget is required to maximize the amount of information gathered from the world - appears in practice across a wide range of applications in autonomous exploration and inspection with mobile robots.
no code implementations • 17 Oct 2016 • Wen Sun, Debadeepta Dey, Ashish Kapoor
To address this problem, we first study the full information setting where in each round the learner receives an adversarial convex loss and a convex constraint.
no code implementations • 16 Sep 2016 • Wen Sun, Niteesh Sood, Debadeepta Dey, Gireeja Ranade, Siddharth Prakash, Ashish Kapoor
This paper explores the problem of path planning under uncertainty.
no code implementations • ICCV 2015 • Debadeepta Dey, Varun Ramakrishna, Martial Hebert, J. Andrew Bagnell
We present a simple approach for producing a small number of structured visual outputs which have high recall, for a variety of tasks including monocular pose estimation and semantic scene segmentation.
no code implementations • 24 Nov 2014 • Debadeepta Dey, Kumar Shaurya Shankar, Sam Zeng, Rupesh Mehta, M. Talha Agcayazi, Christopher Eriksen, Shreyansh Daftry, Martial Hebert, J. Andrew Bagnell
Cameras provide a rich source of information while being passive, cheap and lightweight for small and medium Unmanned Aerial Vehicles (UAVs).
no code implementations • 16 Aug 2013 • Jiaji Zhou, Stephane Ross, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
We study the problem of predicting a set or list of options under knapsack constraint.
no code implementations • 11 May 2013 • Stephane Ross, Jiaji Zhou, Yisong Yue, Debadeepta Dey, J. Andrew Bagnell
Many prediction domains, such as ad placement, recommendation, trajectory prediction, and document summarization, require predicting a set or list of options.