Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Sabach, Shoham"'
In this paper, we study convex bi-level optimization problems where both the inner and outer levels are given as a composite convex minimization. We propose the Fast Bi-level Proximal Gradient (FBi-PG) algorithm, which can be interpreted as applying
Externí odkaz:
http://arxiv.org/abs/2407.21221
We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ensuring that the parameters of these two networks are equivalent. We pro
Externí odkaz:
http://arxiv.org/abs/2406.01838
Publikováno v:
Open Journal of Mathematical Optimization, Vol 1, Iss , Pp 1-15 (2020)
In this paper, we propose a catalog of iterative methods for solving the Split Feasibility Problem in the non-convex setting. We study four different optimization formulations of the problem, where each model has advantages in different settings of t
Externí odkaz:
https://doaj.org/article/b1b1fdde862241498a917bc66ed647f1
Autor:
Ozkara, Kaan, Karakus, Can, Raman, Parameswaran, Hong, Mingyi, Sabach, Shoham, Kveton, Branislav, Cevher, Volkan
Following the introduction of Adam, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this work, we introduce Meta-Adaptiv
Externí odkaz:
http://arxiv.org/abs/2401.08893
Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate
Autor:
Jiang, Ruichen, Raman, Parameswaran, Sabach, Shoham, Mokhtari, Aryan, Hong, Mingyi, Cevher, Volkan
Second-order optimization methods, such as cubic regularized Newton methods, are known for their rapid convergence rates; nevertheless, they become impractical in high-dimensional problems due to their substantial memory requirements and computationa
Externí odkaz:
http://arxiv.org/abs/2401.03058
Autor:
Liu, Zuxin, Zhang, Jesse, Asadi, Kavosh, Liu, Yao, Zhao, Ding, Sabach, Shoham, Fakoor, Rasool
The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large models for su
Externí odkaz:
http://arxiv.org/abs/2310.05905
Autor:
Merchav, Roey, Sabach, Shoham
In this paper, we propose the Bi-Sub-Gradient (Bi-SG) method, which is a generalization of the classical sub-gradient method to the setting of convex bi-level optimization problems. This is a first-order method that is very easy to implement in the s
Externí odkaz:
http://arxiv.org/abs/2307.08245
We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common approach to
Externí odkaz:
http://arxiv.org/abs/2306.17833
We study the convergence behavior of the celebrated temporal-difference (TD) learning algorithm. By looking at the algorithm through the lens of optimization, we first argue that TD can be viewed as an iterative optimization algorithm where the funct
Externí odkaz:
http://arxiv.org/abs/2306.17750
This paper considers a convex composite optimization problem with affine constraints, which includes problems that take the form of minimizing a smooth convex objective function over the intersection of (simple) convex sets, or regularized with multi
Externí odkaz:
http://arxiv.org/abs/2210.13968