Picture for Gantavya Bhatt

Gantavya Bhatt

Matryoshka Representations for Adaptive Deployment

Jun 01, 2022
Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham Kakade, Prateek Jain, Ali Farhadi

Figure 1 for Matryoshka Representations for Adaptive Deployment

Figure 2 for Matryoshka Representations for Adaptive Deployment

Figure 3 for Matryoshka Representations for Adaptive Deployment

Figure 4 for Matryoshka Representations for Adaptive Deployment

* 32 pages, 11 figures Edits: Fixed details about adaptive classification

Access Paper or Ask Questions

Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models

Mar 07, 2021
Hritik Bansal, Gantavya Bhatt, Pankaj Malhotra, Prathosh A. P

Figure 1 for Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models

Figure 2 for Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models

Figure 3 for Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models

Figure 4 for Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models

* 9 pages, 8 figures, 2 tables

Access Paper or Ask Questions

Systematic Generalization for Predictive Control in Multivariate Time Series

Feb 10, 2021
Hritik Bansal, Gantavya Bhatt, Pankaj Malhotra, Prathosh A. P

Figure 1 for Systematic Generalization for Predictive Control in Multivariate Time Series

Figure 2 for Systematic Generalization for Predictive Control in Multivariate Time Series

Figure 3 for Systematic Generalization for Predictive Control in Multivariate Time Series

Figure 4 for Systematic Generalization for Predictive Control in Multivariate Time Series

* 8 pages, 8 figures, 2 tables

Access Paper or Ask Questions

Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?

Oct 10, 2020
Hritik Bansal, Gantavya Bhatt, Sumeet Agarwal

Figure 1 for Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?

Figure 2 for Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?

Figure 3 for Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?

Figure 4 for Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?

* 15 pages, 3 figures, 13 Tables (including Appendix); Submitted for review

Access Paper or Ask Questions

How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?

May 25, 2020
Gantavya Bhatt, Hritik Bansal, Rishubh Singh, Sumeet Agarwal

Figure 1 for How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?

Figure 2 for How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?

Figure 3 for How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?

Figure 4 for How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?

* 11 pages, 5 figures (including appendix); to appear at ACL SRW 2020

Access Paper or Ask Questions