Related papers: Latency-Aware Neural Architecture Search with Mult…
We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given…
This work poses a distributed multi-resource allocation scheme for minimizing the weighted sum of latency and energy consumption in the on-device distributed federated learning (FL) system. Each mobile device in the system engages the model…
Novelty search (NS) refers to a class of exploration algorithms that seek to uncover diverse system behaviors through simulations or experiments. Such diversity is central to many AI-driven discovery and design tasks, including material and…
In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models. Latent variables indeed encode both transferable distributional information and…
Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural…
In the fast-moving world of AI, as organizations and researchers develop more advanced models, they face challenges due to their sheer size and computational demands. Deploying such models on edge devices or in resource-constrained…
Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we…
High Power Targetry (HPT) R&D is critical in the context of increasing beam intensity and energy for next generation accelerators. Many target concepts and novel materials are being developed and tested for their ability to withstand…
In this paper, we point out that differential architecture search (DARTS) makes gradient of architecture parameters biased for network weights and architecture parameters are updated in different datasets alternatively in the bi-level…
Accurate surface roughness prediction is critical for ensuring high product quality, especially in areas like manufacturing and aerospace, where the smallest imperfections can compromise performance or safety. However, this is challenging…
Pareto front profiling in multi-objective optimization (MOO), i.e., finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives that require training a neural network. Typically, in MOO for neural…
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…
Bayesian optimization is a sequential method for minimizing objective functions that are expensive to evaluate and about which few assumptions can be made. By using all gathered data to train a Gaussian process model for the function and…
In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture…
Almost in every heavily computation-dependent application, from 6G communication systems to autonomous driving platforms, a large portion of computing should be near to the client side. Edge computing (AI at Edge) in mobile devices is one…
The phenomenon of adversarial examples has been revealed in variant scenarios. Recent studies show that well-designed adversarial defense strategies can improve the robustness of deep learning models against adversarial examples. However,…
Online field experiments are the gold-standard way of evaluating changes to real-world interactive machine learning systems. Yet our ability to explore complex, multi-dimensional policy spaces - such as those found in recommendation and…
Software architecture optimization aims to enhance non-functional attributes like performance and reliability while meeting functional requirements. Multi-objective optimization employs metaheuristic search techniques, such as genetic…
Searching large and complex design spaces for a global optimum can be infeasible and unnecessary. A practical alternative is to iteratively refine the neighborhood of an initial design using local optimization methods such as gradient…
The pervasive integration of Artificial Intelligence models into contemporary mobile computing is notable across numerous use cases, from virtual assistants to advanced image processing. Optimizing the mobile user experience involves…