Related papers: Feasible-First Exploration for Constrained ML Depl…
Distributed execution of deep learning training involves a dynamic interplay between hardware accelerator architecture and device placement strategy. This is the first work to explore the co-optimization of determining the optimal…
In this paper, we present a novel technique to search for hardware architectures of accelerators optimized for end-to-end training of deep neural networks (DNNs). Our approach addresses both single-device and distributed pipeline and tensor…
In this paper we propose an annealing based framework to incorporate inequality constraints in optimization problems such as facility location, simultaneous facility location with path optimization, and the last mile delivery problem. These…
We study unconstrained smooth convex optimization under stochastic first- and zeroth-order oracles subject only to finite-moment bounds, naturally admitting persistent bias and heavy-tailed noise. In this hostile environment, integrating…
The generalization abilities of heuristic optimizers may deteriorate with the increment of the search space dimensionality. To achieve generalized performance across Large Scale Blackbox Optimization (LSBO) tasks, it ispossible to ensemble…
In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the…
The process of optimizing the latency of DNN operators with ML models and hardware-in-the-loop, called auto-tuning, has established itself as a pervasive method for the deployment of neural networks. From a search space of…
The aim of this paper is twofold. First, we introduce "resource constraints" as a general concept that covers many practical restrictions on experimental design. Second, for computing efficient exact designs of experiments under any…
Bayesian optimization (BO) is an efficient framework for optimization of black-box objectives when function evaluations are costly and gradient information is not easily accessible. BO has been successfully applied to automate the task of…
Resource-intensive computations are a major factor that limits the effectiveness of automated machine learning solutions. In the paper, we propose a modular approach that can be used to increase the quality of evolutionary optimization for…
Efficient exploration remains one of the longstanding problems of deep reinforcement learning. Instead of depending solely on extrinsic rewards from the environments, existing methods use intrinsic rewards to enhance exploration. However,…
Energy systems optimization problems are complex due to strongly non-linear system behavior and multiple competing objectives, e.g. economic gain vs. environmental impact. Moreover, a large number of input variables and different variable…
In this paper we address the optimal planning of autonomous teams for general purpose tasks including a wide spectrum of situations: from project management of human teams to the coordination of an automated assembly lines, focusing in the…
How should Large Language Model (LLM) practitioners select the right model for a task without wasting money? We introduce BELLA (Budget-Efficient LLM Selection via Automated skill-profiling), a framework that recommends optimal LLM…
Black-box optimization (BBO) involves functions that are unknown, inexact and/or expensive-to-evaluate. Existing BBO algorithms face several challenges, including high computational cost from extensive evaluations, difficulty in handling…
The hm admissible heuristics for (sequential and temporal) regression planning are defined by a parameterized relaxation of the optimal cost function in the regression search space, where the parameter m offers a trade-off between the…
The rapid advancement of GPU technology has unlocked powerful parallel processing capabilities, creating new opportunities to enhance classic search algorithms. This hardware has been exploited in best-first search algorithms with neural…
Transfer-based attacks craft adversarial examples on white-box surrogate models and directly deploy them against black-box target models, offering model-agnostic and query-free threat scenarios. While flatness-enhanced methods have recently…
Hierarchical learning algorithms that gradually approximate a solution to a data-driven optimization problem are essential to decision-making systems, especially under limitations on time and computational resources. In this study, we…
This paper presents a novel two-stage flexible dynamic decision support based optimal threat evaluation and defensive resource scheduling algorithm for multi-target air-borne threats. The algorithm provides flexibility and optimality by…