101 citations · 389 across the 29 of their papers we have counts for
17 papers · 1 filter
Zero-th Order Algorithm for Softmax Attention Optimization
Yichuan Deng, Zhihang Li, Sridhar Mahadevan +1
Large language models (LLMs) have brought about significant transformations in human society. Among the crucial computations in LLMs, the softmax unit holds great importance. Its h…
An Over-parameterized Exponential Regression
Yeqi Gao, Sridhar Mahadevan, Zhao Song
Over the past few years, there has been a significant amount of research focused on studying the ReLU activation function, with the aim of achieving neural network convergence thro…
Smoothed Online Combinatorial Optimization Using Imperfect Predictions
Kai Wang, Zhao Song, Georgios Theocharous +1
Smoothed online combinatorial optimization considers a learner who repeatedly chooses a combinatorial decision to minimize an unknown changing cost function with a penalty on switc…
Multiscale Manifold Warping
Sridhar Mahadevan, Anup Rao, Georgios Theocharous +1
Many real-world applications require aligning two temporal sequences, including bioinformatics, handwriting recognition, activity recognition, and human-robot coordination. Dynamic…
Finite-Sample Analysis of Proximal Gradient TD Algorithms
Bo Liu, Ji Liu, Mohammad Ghavamzadeh +2
In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techni…
Regularized Off-Policy TD-Learning
Bo Liu, Sridhar Mahadevan, Ji Liu
We present a novel regularized off-policy convergent TD-learning method (termed RO-TD), which is able to learn sparse representations of value functions with low computationa…