no code implementations • 2 Feb 2024 • Mircea Petrache, Shubhendu Trivedi
Compositional generalization is one of the main properties which differentiates lexical learning in humans from state-of-art neural networks.
1 code implementation • 30 May 2023 • Zhen Lin, Shubhendu Trivedi, Jimeng Sun
Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains.
1 code implementation • 2 Feb 2023 • Zhen Lin, Shubhendu Trivedi, Cao Xiao, Jimeng Sun
We focus on a typical scenario where such requirements, separately encoding $\textit{value}$ and $\textit{cost}$, compete with each other.
1 code implementation • 25 May 2022 • Zhen Lin, Shubhendu Trivedi, Jimeng Sun
We focus on the task of constructing valid prediction intervals (PIs) in time series regression with a cross-section.
no code implementations • 20 May 2022 • Zhen Lin, Shubhendu Trivedi, Jimeng Sun
TQA adjusts the quantile to query in CP at each time $t$, accounting for both cross-sectional and longitudinal coverage in a theoretically-grounded manner.
no code implementations • 15 Feb 2022 • Zhen Lin, Shubhendu Trivedi, Jimeng Sun
Most existing calibration methods either lack theoretical guarantees for producing calibrated outputs, reduce classification accuracy in the process, or only calibrate the predicted class.
1 code implementation • ICLR 2022 • Matthew Farrell, Blake Bordelon, Shubhendu Trivedi, Cengiz Pehlevan
We find that the fraction of separable dichotomies is determined by the dimension of the space that is fixed by the group action.
1 code implementation • NeurIPS 2021 • Zhen Lin, Shubhendu Trivedi, Jimeng Sun
Moreover, when combined with deep learning (DL) methods, it should be scalable and affect the DL model performance minimally.
no code implementations • 25 Feb 2021 • Zhen Lin, Nicholas Huang, Camille Avestruz, W. L. Kimmy Wu, Shubhendu Trivedi, João Caldeira, Brian Nord
We present a comparison between two methods of cluster identification: the standard Matched Filter (MF) method in SZ cluster finding and a method using Convolutional Neural Networks (CNN).
no code implementations • 8 Dec 2020 • Suhas Lohit, Shubhendu Trivedi
These newly proposed convolutional layers naturally extend the notion of convolution to functions on the unit sphere $S^2$ and the group of rotations $SO(3)$ and these layers are equivariant to 3D rotations.
no code implementations • 5 Jun 2020 • Shubhendu Trivedi, J. Wang
The expected gradient outerproduct (EGOP) of an unknown regression function is an operator that arises in the theory of multi-index regression, and is known to recover those directions that are most relevant to predicting the output.
no code implementations • 10 Oct 2019 • Pramod Kaushik Mudrakarta, Shubhendu Trivedi, Risi Kondor
Multiresolution Matrix Factorization (MMF) was recently introduced as an alternative to the dominant low-rank paradigm in order to capture structure in matrices at multiple different scales.
no code implementations • 10 Sep 2019 • Kirk Swanson, Shubhendu Trivedi, Joshua Lequieu, Kyle Swanson, Risi Kondor
The characterization of amorphous materials is especially challenging because their lack of long-range order makes it difficult to define structural metrics.
no code implementations • NeurIPS 2018 • Risi Kondor, Zhen Lin, Shubhendu Trivedi
Recent work by Cohen et al. has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis.
1 code implementation • 2 Oct 2018 • João Caldeira, W. L. Kimmy Wu, Brian Nord, Camille Avestruz, Shubhendu Trivedi, Kyle T. Story
In this work, we demonstrate reconstruction of the CMB lensing potential with deep convolutional neural networks (CNN) - ie, a ResUNet.
no code implementations • 30 Aug 2018 • Shubhendu Trivedi
We also present extensions of this formulation to metric learning for kNN regression, asymmetric similarity learning and discriminative learning of Hamming distance.
1 code implementation • 24 Jun 2018 • Risi Kondor, Zhen Lin, Shubhendu Trivedi
Recent work by Cohen \emph{et al.} has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis.
no code implementations • ICML 2018 • Risi Kondor, Shubhendu Trivedi
In this paper we give a rigorous, theoretical treatment of convolution and equivariance in neural networks with respect to not just translations, but the action of any compact group.
2 code implementations • ICLR 2018 • Risi Kondor, Hy Truong Son, Horace Pan, Brandon Anderson, Shubhendu Trivedi
Most existing neural networks for learning graphs address permutation invariance by conceiving of the network as a message passing scheme, where each node sums the feature vectors coming from its neighbors.
no code implementations • 21 Sep 2015 • Shubhendu Trivedi, Zachary A. Pardos, Neil T. Heffernan
Previous work has hinted at the improvement in prediction accuracy attributed to clustering algorithms if used to pre-process the data.
no code implementations • NeurIPS 2014 • Shubhendu Trivedi, David Mcallester, Greg Shakhnarovich
We formulate the problem of metric learning for k nearest neighbor classification as a large margin structured prediction problem, with a latent variable representing the choice of neighbors and the task loss directly corresponding to classification error.