亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard loss-based fine-tuning may fail to recover accuracy, especially at high sparsities. To address this, we perform a detailed study of distillation-type losses, determining an L2-based distillation approach we term SquareHead which enables accurate recovery even at higher sparsities, across all model types. On the practical efficiency side, we show that sparse LLMs can be executed with speedups by taking advantage of sparsity, for both CPU and GPU runtimes. While the standard approach is to leverage sparsity for computational reduction, we observe that in the case of memory-bound LLMs sparsity can also be leveraged for reducing memory bandwidth. We exhibit end-to-end results showing speedups due to sparsity, while recovering accuracy, on T5 (language translation), Whisper (speech translation), and open GPT-type (MPT for text generation). For MPT text generation, we show for the first time that sparse fine-tuning can reach 75% sparsity without accuracy drops, provide notable end-to-end speedups for both CPU and GPU inference, and highlight that sparsity is also compatible with quantization approaches. Models and software for reproducing our results are provided in Section 6.

The rapid growth of decentralized energy resources and especially Electric Vehicles (EV), that are expected to increase sharply over the next decade, will put further stress on existing power distribution networks, increasing the need for higher system reliability and flexibility. In an attempt to avoid unnecessary network investments and to increase the controllability over distribution networks, network operators develop demand response (DR) programs that incentivize end users to shift their consumption in return for financial or other benefits. Artificial intelligence (AI) methods are in the research forefront for residential load scheduling applications, mainly due to their high accuracy, high computational speed and lower dependence on the physical characteristics of the models under development. The aim of this work is to identify households' EV cost-reducing charging policy under a Time-of-Use tariff scheme, with the use of Deep Reinforcement Learning, and more specifically Deep Q-Networks (DQN). A novel end users flexibility potential reward is inferred from historical data analysis, where households with solar power generation have been used to train and test the designed algorithm. The suggested DQN EV charging policy can lead to more than 20% of savings in end users electricity bills.

Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveraging a few demonstrations pertaining to a new downstream task as conditions. However, this particular learning paradigm suffers from high instability stemming from substantial variances induced by factors such as the input distribution of selected examples, their ordering, and prompt formats. In this work, we demonstrate that even when all these factors are held constant, the random selection of examples still results in high variance. Consequently, we aim to explore the informative ability of data examples by quantifying the Information Gain (IG) obtained in prediction after observing a given example candidate. Then we propose to sample those with maximum IG. Additionally, we identify the presence of template bias, which can lead to unfair evaluations of IG during the sampling process. To mitigate this bias, we introduce Calibration Before Sampling strategy. The experimental results illustrate that our proposed method can yield an average relative improvement of 14.3% across six classification tasks using three LLMs.

The globally convergent convexification numerical method is constructed for a Coefficient Inverse Problem for the Mean Field Games System. A coefficient characterizing the global interaction term is recovered from the single measurement data. In particular, a new Carleman estimate for the Volterra integral operator is proven, and it stronger than the previously known one. Numerical results demonstrate accurate reconstructions from noisy data.

Modern commercial Heating, Ventilation, and Air Conditioning (HVAC) devices form a complex and interconnected thermodynamic system with the building and outside weather conditions, and current setpoint control policies are not fully optimized for minimizing energy use and carbon emission. Given a suitable training environment, a Reinforcement Learning (RL) model is able to improve upon these policies, but training such a model, especially in a way that scales to thousands of buildings, presents many real world challenges. We propose a novel simulation-based approach, where a customized simulator is used to train the agent for each building. Our open-source simulator (available online: //github.com/google/sbsim) is lightweight and calibrated via telemetry from the building to reach a higher level of fidelity. On a two-story, 68,000 square foot building, with 127 devices, we were able to calibrate our simulator to have just over half a degree of drift from the real world over a six-hour interval. This approach is an important step toward having a real-world RL control system that can be scaled to many buildings, allowing for greater efficiency and resulting in reduced energy consumption and carbon emissions.

Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. The prohibitively expensive training and data collection/curation costs of these models make them valuable Intellectual Property (IP) for organizations. This motivates a vendor-client paradigm, where a vendor trains a large-scale VLM and grants only input-output access to clients on a pay-per-query basis in a black-box setting. The client aims to minimize inference cost by distilling the VLM to a student model using the limited available task-specific data, and further deploying this student model in the downstream application. While naive distillation largely improves the In-Domain (ID) accuracy of the student, it fails to transfer the superior out-of-distribution (OOD) generalization of the VLM teacher using the limited available labeled images. To mitigate this, we propose Vision-Language to Vision-Align, Distill, Predict (VL2V-ADiP), which first aligns the vision and language modalities of the teacher model with the vision modality of a pre-trained student model, and further distills the aligned VLM embeddings to the student. This maximally retains the pre-trained features of the student, while also incorporating the rich representations of the VLM image encoder and the superior generalization of the text embeddings. The proposed approach achieves state-of-the-art results on the standard Domain Generalization benchmarks in a black-box teacher setting, and also when weights of the VLM are accessible.

Surrogate Optimization (SO) algorithms have shown promise for optimizing expensive black-box functions. However, their performance is heavily influenced by hyperparameters related to sampling and surrogate fitting, which poses a challenge to their widespread adoption. We investigate the impact of hyperparameters on various SO algorithms and propose a Hyperparameter Adaptive Search for SO (HASSO) approach. HASSO is not a hyperparameter tuning algorithm, but a generic self-adjusting SO algorithm that dynamically tunes its own hyperparameters while concurrently optimizing the primary objective function, without requiring additional evaluations. The aim is to improve the accessibility, effectiveness, and convergence speed of SO algorithms for practitioners. Our approach identifies and modifies the most influential hyperparameters specific to each problem and SO approach, reducing the need for manual tuning without significantly increasing the computational burden. Experimental results demonstrate the effectiveness of HASSO in enhancing the performance of various SO algorithms across different global optimization test problems.

Many evolutionary algorithms (EAs) take advantage of parallel evaluation of candidates. However, if evaluation times vary significantly, many worker nodes (i.e.,\ compute clients) are idle much of the time, waiting for the next generation to be created. Evolutionary neural architecture search (ENAS), a class of EAs that optimizes the architecture and hyperparameters of deep neural networks, is particularly vulnerable to this issue. This paper proposes a generic asynchronous evaluation strategy (AES) that is then adapted to work with ENAS. AES increases throughput by maintaining a queue of up to $K$ individuals ready to be sent to the workers for evaluation and proceeding to the next generation as soon as $M<<K$ individuals have been evaluated. A suitable value for $M$ is determined experimentally, balancing diversity and efficiency. To showcase the generality and power of AES, it was first evaluated in eight-line sorting network design (a single-population optimization task with limited evaluation-time variability), achieving an over two-fold speedup. Next, it was evaluated in 11-bit multiplexer design (a single-population discovery task with extended variability), where a 14-fold speedup was observed. It was then scaled up to ENAS for image captioning (a multi-population open-ended-optimization task), resulting in an over two-fold speedup. In all problems, a multifold performance improvement was observed, suggesting that AES is a promising method for parallelizing the evolution of complex systems with long and variable evaluation times, such as those in ENAS.

Traumatic brain injury (TBI) can cause cognitive, communication, and psychological challenges that profoundly limit independence in everyday life. Conversational Agents (CAs) can provide individuals with TBI with cognitive and communication support, although little is known about how they make use of CAs to address injury-related needs. In this study, we gave nine adults with TBI an at-home CA for four weeks to investigate use patterns, challenges, and design requirements, focusing particularly on injury-related use. The findings revealed significant gaps between the current capabilities of CAs and accessibility challenges faced by TBI users. We also identified 14 TBI-related activities that participants engaged in with CAs. We categorized those activities into four groups: mental health, cognitive activities, healthcare and rehabilitation, and routine activities. Design implications focus on accessibility improvements and functional designs of CAs that can better support the day-to-day needs of people with TBI.

Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.