Zobrazeno 1 - 10
of 403
pro vyhledávání: '"Grama, Ananth"'
Spectral Graph Convolutional Networks (GCNs) have gained popularity in graph machine learning applications due, in part, to their flexibility in specification of network propagation rules. These propagation rules are often constructed as polynomial f
Externí odkaz:
http://arxiv.org/abs/2409.04813
Task-specific functional MRI (fMRI) images provide excellent modalities for studying the neuronal basis of cognitive processes. We use fMRI data to formulate and solve the problem of deconvolving task-specific aggregate neuronal networks into a set o
Externí odkaz:
http://arxiv.org/abs/2407.00201
Aligning large language models (LLMs) with human preferences is critical for their deployment. Recently, decoding-time alignment has emerged as an effective plug-and-play technique that requires no fine-tuning of model parameters. However, generating
Externí odkaz:
http://arxiv.org/abs/2406.16306
We study online classification of features into labels with general hypothesis classes. In our setting, true labels are determined by some function within the hypothesis class but are corrupted by unknown stochastic noise, and the features are genera
Externí odkaz:
http://arxiv.org/abs/2309.01698
Publikováno v:
Published at Conference on Learning Theory (COLT) 2023; https://proceedings.mlr.press/v195/wu23a.html
We study the problem of online learning and online regret minimization when samples are drawn from a general unknown non-stationary process. We introduce the concept of a dynamic changing process with cost $K$, where the conditional marginals of the
Externí odkaz:
http://arxiv.org/abs/2302.00103
Publikováno v:
Published in Transactions on Machine Learning Research (08/2023). URL: https://openreview.net/forum?id=H1SekypXKA
We study the problem of sequential prediction and online minimax regret with stochastically generated features under a general loss function. We introduce a notion of expected worst case minimax regret that generalizes and encompasses prior known min
Externí odkaz:
http://arxiv.org/abs/2209.04417
Publikováno v:
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
We study the sequential general online regression, known also as the sequential probability assignments, under logarithmic loss when compared against a broad class of experts. We focus on obtaining tight, often matching, lower and upper bounds for th
Externí odkaz:
http://arxiv.org/abs/2205.03728
Autor:
Adib, Riddhiman, Naved, Md Mobasshir Arshed, Fang, Chih-Hao, Gani, Md Osman, Grama, Ananth, Griffin, Paul, Ahamed, Sheikh Iqbal, Adibuzzaman, Mohammad
Structural causal models (SCMs) provide a principled approach to identifying causation from observational and experimental data in disciplines ranging from economics to medicine. However, SCMs, which is typically represented as graphical models, cann
Externí odkaz:
http://arxiv.org/abs/2204.13775
There has been significant recent interest in quantum neural networks (QNNs), along with their applications in diverse domains. Current solutions for QNNs pose significant challenges concerning their scalability, ensuring that the postulates of quant
Externí odkaz:
http://arxiv.org/abs/2203.12092