no code implementations • 15 Apr 2024 • Zhenwei Huang, Wen Huang, Pratik Jawanpuria, Bamdev Mishra
To the best of our knowledge, this is the first federated learning framework on Riemannian manifold with a privacy guarantee and convergence results.
2 code implementations • 10 Apr 2024 • Neel Mishra, Bamdev Mishra, Pratik Jawanpuria, Pawan Kumar
It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse.
no code implementations • 6 Feb 2024 • Andi Han, Bamdev Mishra, Pratik Jawanpuria, Akiko Takeda
We provide convergence and complexity analysis for the proposed hypergradient descent algorithm on manifolds.
1 code implementation • 20 Apr 2023 • Istasis Mishra, Arpan Dasgupta, Pratik Jawanpuria, Bamdev Mishra, Pawan Kumar
Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels.
no code implementations • 30 Nov 2022 • Souvik Banerjee, Bamdev Mishra, Pratik Jawanpuria, Manish Shrivastava
The proposed modelling and the novel similarity metric exploits the matrix structure of embeddings.
1 code implementation • 10 Oct 2022 • Saiteja Utpala, Andi Han, Pratik Jawanpuria, Bamdev Mishra
We present Rieoptax, an open source Python library for Riemannian optimization in JAX.
no code implementations • 4 Oct 2022 • Arghya Roy Chaudhuri, Pratik Jawanpuria, Bamdev Mishra
In this work, we propose a multi-armed bandit-based framework for identifying a compact set of informative data instances (i. e., the prototypes) from a source dataset $S$ that best represents a given target set $T$.
no code implementations • 13 Aug 2022 • Andi Han, Bamdev Mishra, Pratik Jawanpuria, Junbin Gao
In this paper, we propose a simple acceleration scheme for Riemannian gradient methods by extrapolating iterates on manifolds.
no code implementations • 19 May 2022 • Andi Han, Bamdev Mishra, Pratik Jawanpuria, Junbin Gao
We introduce a framework of differentially private Riemannian optimization by adding noise to the Riemannian gradient on the tangent space.
no code implementations • 25 Apr 2022 • Andi Han, Bamdev Mishra, Pratik Jawanpuria, Pawan Kumar, Junbin Gao
In this paper, we study min-max optimization problems on Riemannian manifolds.
no code implementations • 3 Apr 2022 • Soumyadeep Dey, Pratik Jawanpuria
Foreground-background separation is an important problem in document image analysis.
1 code implementation • 30 Jan 2022 • Andi Han, Bamdev Mishra, Pratik Jawanpuria, Junbin Gao
In this work, we study the optimal transport (OT) problem between symmetric positive definite (SPD) matrix-valued measures.
1 code implementation • 20 Oct 2021 • Andi Han, Bamdev Mishra, Pratik Jawanpuria, Junbin Gao
Learning with symmetric positive definite (SPD) matrices has many applications in machine learning.
1 code implementation • NeurIPS 2021 • Andi Han, Bamdev Mishra, Pratik Jawanpuria, Junbin Gao
We build on this to show that the BW metric is a more suitable and robust choice for several Riemannian optimization problems over ill-conditioned SPD matrices.
1 code implementation • 19 May 2021 • Soumyadeep Dey, Pratik Jawanpuria
Smartphones have enabled effortless capturing and sharing of documents in digital form.
no code implementations • 18 Mar 2021 • Karthik S. Gurumoorthy, Pratik Jawanpuria, Bamdev Mishra
In this work, we develop an optimal transport (OT) based framework to select informative prototypical examples that best represent a given target dataset.
1 code implementation • 1 Mar 2021 • Bamdev Mishra, N T V Satyadev, Hiroyuki Kasai, Pratik Jawanpuria
In this work, we discuss how to computationally approach general non-linear OT problems within the framework of Riemannian manifold optimization.
1 code implementation • 10 Nov 2020 • Piyushi Manupriya, J. Saketha Nath, Pratik Jawanpuria
Further, for real-world applications involving non-discrete measures, we present an estimator for the transport plan that is supported only on the given ($m$) samples.
2 code implementations • 22 Oct 2020 • Pratik Jawanpuria, N T V Satyadev, Bamdev Mishra
Optimal transport (OT) is a powerful geometric tool for comparing two distributions and has been employed in various machine learning applications.
no code implementations • WS 2020 • Pratik Jawanpuria, N T V Satya Dev, Anoop Kunchukuttan, Bamdev Mishra
We propose a geometric framework for learning meta-embeddings of words from different embedding sources.
no code implementations • EMNLP 2020 • Pratik Jawanpuria, Mayank Meghwanshi, Bamdev Mishra
Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision.
no code implementations • ACL 2020 • Pratik Jawanpuria, Mayank Meghwanshi, Bamdev Mishra
We propose a novel manifold based geometric approach for learning unsupervised alignment of word embeddings between the source and the target languages.
no code implementations • NeurIPS 2020 • J. Saketha Nath, Pratik Jawanpuria
This work takes the novel approach of posing statistical OT as that of learning the transport plan's kernel mean embedding from sample based estimates of marginal embeddings.
no code implementations • 25 Jun 2019 • Bamdev Mishra, Hiroyuki Kasai, Pratik Jawanpuria
In this work, we generalize the probability simplex constraint to matrices, i. e., $\mathbf{X}_1 + \mathbf{X}_2 + \ldots + \mathbf{X}_K = \mathbf{I}$, where $\mathbf{X}_i \succeq 0$ is a symmetric positive semidefinite matrix of size $n\times n$ for all $i = \{1,\ldots, K \}$.
no code implementations • 18 Mar 2019 • Pratik Jawanpuria, Mayank Meghwanshi, Bamdev Mishra
While the hyperbolic manifold is well-studied in the literature, it has gained interest in the machine learning and natural language processing communities lately due to its usefulness in modeling continuous hierarchies.
1 code implementation • 4 Feb 2019 • Hiroyuki Kasai, Pratik Jawanpuria, Bamdev Mishra
We propose novel stochastic gradient algorithms for problems on Riemannian matrix manifolds by adapting the row and column subspaces of gradients.
1 code implementation • 3 Oct 2018 • Mayank Meghwanshi, Pratik Jawanpuria, Anoop Kunchukuttan, Hiroyuki Kasai, Bamdev Mishra
In this paper, we introduce McTorch, a manifold optimization library for deep learning that extends PyTorch.
2 code implementations • TACL 2019 • Pratik Jawanpuria, Arjun Balgovind, Anoop Kunchukuttan, Bamdev Mishra
Our approach decouples learning the transformation from the source language to the target language into (a) learning rotations for language-specific embeddings to align them to a common space, and (b) learning a similarity metric in the common space to model similarities between the embeddings.
1 code implementation • ICML 2018 • Pratik Jawanpuria, Bamdev Mishra
We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices.
1 code implementation • 14 Jun 2018 • Mukul Bhutani, Pratik Jawanpuria, Hiroyuki Kasai, Bamdev Mishra
We propose a low-rank approach to learning a Mahalanobis metric from data.
no code implementations • NeurIPS 2018 • Madhav Nimishakavi, Pratik Jawanpuria, Bamdev Mishra
One of the popular approaches for low-rank tensor completion is to use the latent trace norm regularization.
no code implementations • 1 May 2017 • Bamdev Mishra, Hiroyuki Kasai, Pratik Jawanpuria, Atul Saroop
Interesting applications in this setting include low-rank matrix completion and low-dimensional multivariate regression, among others.
no code implementations • 24 Apr 2017 • Pratik Jawanpuria, Bamdev Mishra
We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices.
no code implementations • NeurIPS 2015 • Pratik Jawanpuria, Maksim Lapin, Matthias Hein, Bernt Schiele
The paradigm of multi-task learning is that one can achieve better generalization by learning tasks jointly and thus exploiting the similarity between the tasks rather than learning them independently of each other.