Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Mishra, Bamdev"'
Autor:
Manupriya, Piyushi, Jawanpuria, Pratik, Gurumoorthy, Karthik S., Jagarlapudi, SakethaNath, Mishra, Bamdev
Unbalanced optimal transport (UOT) has recently gained much attention due to its flexible framework for handling un-normalized measures and its robustness properties. In this work, we explore learning (structured) sparse transport plans in the UOT se
Externí odkaz:
http://arxiv.org/abs/2406.04914
Many machine learning applications are naturally formulated as optimization problems on Riemannian manifolds. The main idea behind Riemannian optimization is to maintain the feasibility of the variables while moving along a descent direction on the m
Externí odkaz:
http://arxiv.org/abs/2406.02225
Autor:
Han, Andi, Li, Jiaxiang, Huang, Wei, Hong, Mingyi, Takeda, Akiko, Jawanpuria, Pratik, Mishra, Bamdev
Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank structures on weig
Externí odkaz:
http://arxiv.org/abs/2406.02214
In recent years, federated learning (FL) has emerged as a prominent paradigm in distributed machine learning. Despite the partial safeguarding of agents' information within FL systems, a malicious adversary can potentially infer sensitive information
Externí odkaz:
http://arxiv.org/abs/2404.10029
A novel first-order method is proposed for training generative adversarial networks (GANs). It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse. The method co
Externí odkaz:
http://arxiv.org/abs/2404.07172
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 107-120 (2019)
We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples the source-to-target language transformation into (a) language-specific rotations on the original em
Externí odkaz:
https://doaj.org/article/0106d85beca640c29a30d8d945f56b67
Bilevel optimization has seen an increasing presence in various domains of applications. In this work, we propose a framework for solving bilevel optimization problems where variables of both lower and upper level problems are constrained on Riemanni
Externí odkaz:
http://arxiv.org/abs/2402.03883
Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels. Hence, scalability of the classifier with increasing label dimension is an important consideration. In this paper,
Externí odkaz:
http://arxiv.org/abs/2304.11045
This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius
Externí odkaz:
http://arxiv.org/abs/2211.16801
We present Rieoptax, an open source Python library for Riemannian optimization in JAX. We show that many differential geometric primitives, such as Riemannian exponential and logarithm maps, are usually faster in Rieoptax than existing frameworks in
Externí odkaz:
http://arxiv.org/abs/2210.04840