Related papers: Apollo: Transferable Architecture Exploration
Low-thrust electric propulsion missions are often designed under simplifying assumptions such as constant thrust or fixed specific impulse, neglecting the strong coupling between trajectory dynamics, spacecraft power availability, and…
The paper provides a comprehensive overview of Neural Architecture Search (NAS), emphasizing its evolution from manual design to automated, computationally-driven approaches. It covers the inception and growth of NAS, highlighting its…
Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…
The discovery of extremal structures in mathematics requires navigating vast and nonconvex landscapes where analytical methods offer little guidance and brute-force search becomes intractable. We introduce FlowBoost, a closed-loop…
Multi-accelerator servers are increasingly being deployed in shared multi-tenant environments (such as in cloud data centers) in order to meet the demands of large-scale compute-intensive workloads. In addition, these accelerators are…
For decades, Moore's Law has served as a steadfast pillar in computer architecture and system design, promoting a clear abstraction between hardware and software. This traditional Moore's computing paradigm has deepened the rift between the…
Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of the agent's policy can affect its exploration capabilities.…
In robotics, structural design and behavior optimization have long been considered separate processes, resulting in the development of systems with limited capabilities. Recently, co-design methods have gained popularity, where bi-level…
In this work, we present a systematic study of this trade-off from a deployment-centric perspective, focusing on an autonomous driving scenario. Instead of treating overlay and customized acceleration as isolated design points, we analyze…
Evolutionary Computation algorithms have been used to solve optimization problems in relation with architectural, hyper-parameter or training configuration, forging the field known today as Neural Architecture Search. These algorithms have…
Advancements in mathematical programming have made it possible to efficiently tackle large-scale real-world problems that were deemed intractable just a few decades ago. However, provably optimal solutions may not be accepted due to the…
In recent times, an increasing number of researchers have been devoted to utilizing deep neural networks for end-to-end flight navigation. This approach has gained traction due to its ability to bridge the gap between perception and…
This paper was prompted by numerical experiments we performed, in which algorithms already available in the literature (DVS-BDDM) yielded accelerations (or speedups) many times larger (more than seventy in some examples already treated, but…
Computer modeling is essential to research on Advanced Accelerator Concepts (AAC), as well as to their design and operation. This paper summarizes the current status and future needs of AAC systems and reports on several key aspects of (i)…
Model-Agnostic Meta-Learning (MAML) and its variants have achieved success in meta-learning tasks on many datasets and settings. On the other hand, we have just started to understand and analyze how they are able to adapt fast to new tasks.…
The fine-grained relationship between form and function with respect to deep neural network architecture design and hardware-specific acceleration is one area that is not well studied in the research literature, with form often dictated by…
Generation and exploration of approximate circuits and accelerators has been a prominent research domain to achieve energy-efficiency and/or performance improvements. This research has predominantly focused on ASICs, while not achieving…
Many recent works have designed accelerators for Convolutional Neural Networks (CNNs). While digital accelerators have relied on near data processing, analog accelerators have further reduced data movement by performing in-situ computation.…
Application autotuning is a promising path investigated in literature to improve computation efficiency. In this context, the end-users define high-level requirements and an autonomic manager is able to identify and seize optimization…
Amorphous multi-element materials offer unprecedented tunability in composition and properties, yet their rational design remains challenging due to the lack of predictive structure-property relationships and the vast configurational space.…