The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically selected from the original image with reinforcement learning. Such a dynamic decision process naturally facilitates adaptive inference at test time, i.e., it can be terminated once the model is sufficiently confident about its prediction and thus avoids further redundant computation. Notably, our framework is general and flexible as it is compatible with most of the state-of-the-art light-weighted CNNs (such as MobileNets, EfficientNets and RegNets), which can be conveniently deployed as the backbone feature extractor. Experiments on ImageNet show that our method consistently improves the computational efficiency of a wide variety of deep models. For example, it further reduces the average latency of the highly efficient MobileNet-V3 on an iPhone XS Max by 20% without sacrificing accuracy.

Two-stage stochastic programs (2SPs) are important tools for making decisions under uncertainty. Decision-makers use contextual information to generate a set of scenarios to represent the true conditional distribution. However, the number of scenarios required is a barrier to implementing 2SPs, motivating the problem of generating a small set of surrogate scenarios that yield high-quality decisions when they represent uncertainty. Current scenario generation approaches do not leverage contextual information or do not address computational concerns. In response, we propose contextual scenario generation (CSG) to learn a mapping between the context and a set of surrogate scenarios of user-specified size. First, we propose a distributional approach that learns the mapping by minimizing a distributional distance between the predicted surrogate scenarios and the true contextual distribution. Second, we propose a task-based approach that aims to produce surrogate scenarios that yield high-quality decisions. The task-based approach uses neural architectures to approximate the downstream objective and leverages the approximation to search for the mapping. The proposed approaches apply to various problem structures and loosely only require efficient solving of the associated subproblems and 2SPs defined on the reduced scenario sets. Numerical experiments demonstrating the effectiveness of the proposed methods are presented.

Weaknesses: Post rebuttal edit: The extra experiments comparing to random did convince me that GFNet does something beyond random. But I'm still not convinced that GFNets are particularly smart at glancing. Note (from table 1 of the rebuttal) for instance that to reach sota accuracy, it looks like a fovea/glance of size 1/n of the original window seems to need n steps. To me this seems that glancing barely pays for itself. In fact, if you replaced random foveation with deterministic uniform coverage of the image, you may have done better.

Four knowledgeable referees support acceptance for the contribution; they like the authors' novel idea of Glance and Focus net and ImageNet scale evaluations showing superior accuracy-efficiency tradeoff against state-of-the-art-baselines. Please make it sure to properly include and discuss missing references and experimental comparisons, as promised in the rebuttal.

The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically selected from the original image with reinforcement learning. Such a dynamic decision process naturally facilitates adaptive inference at test time, i.e., it can be terminated once the model is sufficiently confident about its prediction and thus avoids further redundant computation. Notably, our framework is general and flexible as it is compatible with most of the state-of-the-art light-weighted CNNs (such as MobileNets, EfficientNets and RegNets), which can be conveniently deployed as the backbone feature extractor.

With the rise of Large Language Models (LLMs), AI assistants' ability to utilize tools, especially through API calls, has advanced notably. This progress has necessitated more accurate evaluation methods. Many existing studies adopt static evaluation, where they assess AI assistants' API call based on pre-defined dialogue histories. However, such evaluation method can be misleading, as an AI assistant might fail in generating API calls from preceding human interaction in real cases. Instead of the resource-intensive method of direct human-machine interactions, we propose Automated Dynamic Evaluation (AutoDE) to assess an assistant's API call capability without human involvement. In our framework, we endeavor to closely mirror genuine human conversation patterns in human-machine interactions, using a LLM-based user agent, equipped with a user script to ensure human alignment. Experimental results highlight that AutoDE uncovers errors overlooked by static evaluations, aligning more closely with human assessment. Testing four AI assistants using our crafted benchmark, our method further mirrored human evaluation compared to conventional static evaluations.

Millions of vulnerable consumer IoT devices in home networks are the enabler for cyber crimes putting user privacy and Internet security at risk. Internet service providers (ISPs) are best poised to play key roles in mitigating risks by automatically inferring active IoT devices per household and notifying users of vulnerable ones. Developing a scalable inference method that can perform robustly across thousands of home networks is a non-trivial task. This paper focuses on the challenges of developing and applying data-driven inference models when labeled data of device behaviors is limited and the distribution of data changes (concept drift) across time and space domains. Our contributions are three-fold: (1) We collect and analyze network traffic of 24 types of consumer IoT devices from 12 real homes over six weeks to highlight the challenge of temporal and spatial concept drifts in network behavior of IoT devices; (2) We analyze the performance of two inference strategies, namely "global inference" (a model trained on a combined set of all labeled data from training homes) and "contextualized inference" (several models each trained on the labeled data from a training home) in the presence of concept drifts; and (3) To manage concept drifts, we develop a method that dynamically applies the ``closest'' model (from a set) to network traffic of unseen homes during the testing phase, yielding better performance in 20% of scenarios.

ISTRIBUTED heuristics are a promising field for current and future energy systems control and optimization tasks, In [12] we showed that different communication topologies and have been designed and evaluated in recent years on have an effect on the performance of the reflected algorithm agent-based systems [1] [2] [3]. While conventional control class: Highly meshed topologies converged into good solutions systems - centralized or hierarchical in their control paradigm - reliably and quickly, but increased communication overhead and perfectly fit to centralized generation and transmission systems, premature convergence. In contrast, results for sparsely meshed distributed renewable energy systems show properties that topologies were much less reliable. In the application domain promote the application of distributed optimization systems: of energy systems as critical infrastructures, this behavior is First, future energy systems can be regarded as complex highly unwanted. We presume that dynamically adjusting the systems of systems, sometimes framed as cyber-physical multienergy topology during runtime leads to a beneficial transition of systems, coupling communication systems, power, heat exploration and exploitation of the search space for distributed and gas systems.

A recently released market research report shows the market for machine learning growing at a rapid 44.1% compounded annual growth rate over the next five years, driven largely by the financial services sector, where big data can yield critical and actionable business insights. In the world of behavioral biometrics, machine learning, deep learning and artificial intelligence are all hand-in-glove. Behavioral biometrics identifies people by how they interact with devices and online applications. As opposed to something that someone has like a device, token or a static attribute like a fingerprint or a name, behavioral biometrics is a dynamic modality that is completely passive and works in the background, making it impossible to copy or steal. Today's behavioral biometric technologies can capture more than 2,000 parameters from a mobile device, including the way a person holds the phone, scrolls, toggles between fields, the pressure they use when they type and how they respond to different stimuli that are presented in online applications. Behavioral biometrics is used primarily for preventing the use of stolen or synthetic identities in applying for credit online and in preventing account takeovers once a user is logged into a session.