Zobrazeno 1 - 10
of 15 270
pro vyhledávání: '"Krishnakumar AN"'
Autor:
Iraci, F., Chalumeau, A., Tiburzi, C., Verbiest, J. P. W., Possenti, A., Shaifullah, G. M., Susarla, S. C., Krishnakumar, M. A., Lam, M. T., Cromartie, H. T., Kerr, M., Grießmeier, Jean-Mathias
Radio pulsars allow the study of the ionised interstellar medium and its dispersive effects, a major noise source in gravitational wave searches using pulsars. In this paper, we compare the functionality and reliability of three commonly used schemes
Externí odkaz:
http://arxiv.org/abs/2410.22170
We theoretically investigate the in-context learning capabilities of transformers in the context of learning mixtures of linear regression models. For the case of two mixtures, we demonstrate the existence of transformers that can achieve an accuracy
Externí odkaz:
http://arxiv.org/abs/2410.14183
Autor:
Touzel, Maximilian Puelma, Sarangi, Sneheel, Welch, Austin, Krishnakumar, Gayatri, Zhao, Dan, Yang, Zachary, Yu, Hao, Kosak-Hine, Ethan, Gibbs, Tom, Musulan, Andreea, Thibault, Camille, Gurbuz, Busra Tugce, Rabbany, Reihaneh, Godbout, Jean-François, Pelrine, Kellin
The rise of AI-driven manipulation poses significant risks to societal trust and democratic processes. Yet, studying these effects in real-world settings at scale is ethically and logistically impractical, highlighting a need for simulation tools tha
Externí odkaz:
http://arxiv.org/abs/2410.13915
We explore the capability of transformers to address endogeneity in in-context linear regression. Our main finding is that transformers inherently possess a mechanism to handle endogeneity effectively using instrumental variables (IV). First, we demo
Externí odkaz:
http://arxiv.org/abs/2410.01265
Autor:
Huo, Pingyi, Devulapally, Anusha, Maruf, Hasan Al, Park, Minseo, Nair, Krishnakumar, Arunachalam, Meena, Akbulut, Gulsum Gudukbay, Kandemir, Mahmut Taylan, Narayanan, Vijaykrishnan
Deep Learning Recommendation Models (DLRMs) have become increasingly popular and prevalent in today's datacenters, consuming most of the AI inference cycles. The performance of DLRMs is heavily influenced by available bandwidth due to their large vec
Externí odkaz:
http://arxiv.org/abs/2409.16633
Autor:
Susarla, S. C., Chalumeau, A., Tiburzi, C., Keane, E. F., Verbiest, J. P. W., Hazboun, J. S., Krishnakumar, M. A., Iraci, F., Shaifullah, G. M., Golden, A., Nielsen, A. S. Bak, Donner, J., Grießmeier, J. M., Keith, M. J., Osłowski, S., Porayko, N. K., Serylak, M., Anderson, J. M., Brüggen, M., Ciardi, B., Dettmar, R. J., Hoeft, M., Künsemöller, J., Schwarz, D., Vocks, C.
High-precision pulsar timing is highly dependent on precise and accurate modeling of any effects that impact the data. It was shown that commonly used Solar Wind models do not accurately account for variability in the amplitude of the Solar wind on b
Externí odkaz:
http://arxiv.org/abs/2409.09838
We provide finite-particle convergence rates for the Stein Variational Gradient Descent (SVGD) algorithm in the Kernelized Stein Discrepancy ($\mathsf{KSD}$) and Wasserstein-2 metrics. Our key insight is that the time derivative of the relative entro
Externí odkaz:
http://arxiv.org/abs/2409.08469
We develop and analyze algorithms for instrumental variable regression by viewing the problem as a conditional stochastic optimization problem. In the context of least-squares instrumental variable regression, our algorithms neither require matrix in
Externí odkaz:
http://arxiv.org/abs/2405.19463
We study the complexity of heavy-tailed sampling and present a separation result in terms of obtaining high-accuracy versus low-accuracy guarantees i.e., samplers that require only $O(\log(1/\varepsilon))$ versus $\Omega(\text{poly}(1/\varepsilon))$
Externí odkaz:
http://arxiv.org/abs/2405.16736
We explore the minimax optimality of goodness-of-fit tests on general domains using the kernelized Stein discrepancy (KSD). The KSD framework offers a flexible approach for goodness-of-fit testing, avoiding strong distributional assumptions, accommod
Externí odkaz:
http://arxiv.org/abs/2404.08278