Search

In the high-stakes domain of search-and-rescue missions, the deployment of Unmanned Aerial Vehicles (UAVs) has become increasingly pivotal. These missions require seamless, real-time communication among diverse roles within response teams, particularly between Remote Operators (ROs) and On-Site Operators (OSOs). Traditionally, ROs and OSOs have relied on radio communication to exchange critical information, such as the geolocation of victims, hazardous areas, and points of interest. However, radio communication lacks information visualization, suffers from noise, and requires mental effort to interpret information, leading to miscommunications and misunderstandings. To address these challenges, this paper presents VizCom-AR, an Augmented Reality system designed to facilitate visual communication between ROs and OSOs and their situational awareness during UAV-driven search-and-rescue missions. Our experiments, focus group sessions with police officers, and field study showed that VizCom-AR enhances spatial awareness of both ROs and OSOs, facilitate geolocation information exchange, and effectively complement existing communication tools in UAV-driven emergency response missions. Overall, VizCom-AR offers a fundamental framework for designing Augmented Reality systems for large scale UAV-driven rescue missions., Comment: 8 pages

Rapidly evolving artificial intelligence and machine learning applications require ever-increasing computational capabilities, while monolithic 2D design technologies approach their limits. Heterogeneous integration of smaller chiplets using a 2.5D silicon interposer and 3D packaging has emerged as a promising paradigm to address this limit and meet performance demands. These approaches offer a significant cost reduction and higher manufacturing yield than monolithic 2D integrated circuits. However, the compact arrangement and high compute density exacerbate the thermal management challenges, potentially compromising performance. Addressing these thermal modeling challenges is critical, especially as system sizes grow and different design stages require varying levels of accuracy and speed. Since no single thermal modeling technique meets all these needs, this paper introduces MFIT, a range of multi-fidelity thermal models that effectively balance accuracy and speed. These multi-fidelity models can enable efficient design space exploration and runtime thermal management. Our extensive testing on systems with 16, 36, and 64 2.5D integrated chiplets and 16x3 3D integrated chiplets demonstrates that these models can reduce execution times from days to mere seconds and milliseconds with negligible loss in accuracy., Comment: Preprint for MFIT: Multi-Fidelity Thermal Modeling for 2.5D and 3D Multi-Chiplet Architectures

Mixed Integer Linear Programming (MILP) is essential for modeling complex decision-making problems but faces challenges in computational tractability and requires expert formulation. Current deep learning approaches for MILP focus on specific problem classes and do not generalize to unseen classes. To address this shortcoming, we take a foundation model training approach, where we train a single deep learning model on a diverse set of MILP problems to generalize across problem classes. As existing datasets for MILP lack diversity and volume, we introduce MILP-Evolve, a novel LLM-based evolutionary framework that is capable of generating a large set of diverse MILP classes with an unlimited amount of instances. We study our methodology on three key learning tasks that capture diverse aspects of MILP: (1) integrality gap prediction, (2) learning to branch, and (3) a new task of aligning MILP instances with natural language descriptions. Our empirical results show that models trained on the data generated by MILP-Evolve achieve significant improvements on unseen problems, including MIPLIB benchmarks. Our work highlights the potential of moving towards a foundation model approach for MILP that can generalize to a broad range of MILP applications. We are committed to fully open-sourcing our work to advance further research.

In this work, we propose a generalization to the classical logistic map. The generalized map preserves most properties of the classical map and has richer dynamics as it contains the fractional order and one more parameter. We propose the stability bounds for each equilibrium point. The detailed bifurcation analysis with respect to both parameters is presented using the bifurcation diagrams in one and two dimensions. The chaos in this system is controlled using delayed feedback. We provide some non-linear feedback controllers to synchronize the system. The multistability in the proposed system is also discussed., Comment: 25 pages, 46 figures

Ethanolamine (NH2CH2CH2OH) has recently been identified in the molecular cloud G+0.693-0.027, situated in the SgrB2 complex in the Galactic center. However, its presence in other regions, and in particular in star-forming sites, is still elusive. Given its likely role as a precursor to simple amino acids, understanding its presence in the star-forming region is required. Here, we present the experimentally obtained temperature-dependent spectral features and morphological behavior of pure ethanolamine ices under astrochemical conditions in the 2 - 12 micro meter (MIR) and 120 - 230 nm (VUV) regions for the first time. These features would help in understanding its photochemical behavior. In addition, we present the first chemical models specifically dedicated to ethanolamine. These models include all the discussed chemical routes from the literature, along with the estimated binding energies and activation energies from quantum chemical calculations reported in this work. We have found that surface reactions: CH2OH + NH2CH2 --> NH2CH2CH2OH and NH2 + C2H4OH --> NH2CH2CH2OH in warmer regions (60-90 K) could play a significant role in the formation of ethanolamine. Our modeled abundance of ethanolamine complements the upper limit of ethanolamine column density estimated in earlier observations in hot core/corino regions. Furthermore, we provide a theoretical estimation of the rotational and distortional constants for various species (such as HNCCO, NH2CHCO, and NH2CH2CO) related to ethanolamine that have not been studied in existing literature. This study could be valuable for identifying these species in the future., Comment: 18 pages, 6 figures. Accepted for the publication in The Astrophysical Journal

Transformers have revolutionized deep learning and generative modeling to enable unprecedented advancements in natural language processing tasks and beyond. However, designing hardware accelerators for executing transformer models is challenging due to the wide variety of computing kernels involved in the transformer architecture. Existing accelerators are either inadequate to accelerate end-to-end transformer models or suffer notable thermal limitations. In this paper, we propose the design of a three-dimensional heterogeneous architecture referred to as HeTraX specifically optimized to accelerate end-to-end transformer models. HeTraX employs hardware resources aligned with the computational kernels of transformers and optimizes both performance and energy. Experimental results show that HeTraX outperforms existing state-of-the-art by up to 5.6x in speedup and improves EDP by 14.5x while ensuring thermally feasibility., Comment: Presented at ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED-24)

We consider the problem of active learning for global sensitivity analysis of expensive black-box functions. Our aim is to efficiently learn the importance of different input variables, e.g., in vehicle safety experimentation, we study the impact of the thickness of various components on safety objectives. Since function evaluations are expensive, we use active learning to prioritize experimental resources where they yield the most value. We propose novel active learning acquisition functions that directly target key quantities of derivative-based global sensitivity measures (DGSMs) under Gaussian process surrogate models. We showcase the first application of active learning directly to DGSMs, and develop tractable uncertainty reduction and information gain acquisition functions for these measures. Through comprehensive evaluation on synthetic and real-world problems, our study demonstrates how these active learning acquisition strategies substantially enhance the sample efficiency of DGSM estimation, particularly with limited evaluation budgets. Our work paves the way for more efficient and accurate sensitivity analysis in various scientific and engineering applications.

In recent years, insider threats and attacks have been increasing in terms of frequency and cost to the corporate business. The utilization of end-to-end encrypted instant messaging applications (WhatsApp, Telegram, VPN) by malicious insiders raised data breach incidents exponentially. The Securities and Exchange Board of India (SEBI) investigated reports on such data leak incidents and reported about twelve companies where earnings data and financial information were leaked using WhatsApp messages. Recent surveys indicate that 60% of data breaches are primarily caused by malicious insider threats. Especially, in the case of the defense environment, information leaks by insiders will jeopardize the countrys national security. Sniffing of network and host-based activities will not work in an insider threat detection environment due to end-to-end encryption. Memory forensics allows access to the messages sent or received over an end-to-end encrypted environment but with a total compromise of the users privacy. In this research, we present a novel solution to detect data leakages by insiders in an organization. Our approach captures the RAM of the insiders device and analyses it for sensitive information leaks from a host system while maintaining the users privacy. Sensitive data leaks are identified with context using a deep learning model. The feasibility and effectiveness of the proposed idea have been demonstrated with the help of a military use case. The proposed architecture can however be used across various use cases with minor modifications.

We consider the problem of multi-objective optimization (MOO) of expensive black-box functions with the goal of discovering high-quality and diverse Pareto fronts where we are allowed to evaluate a batch of inputs. This problem arises in many real-world applications including penicillin production where diversity of solutions is critical. We solve this problem in the framework of Bayesian optimization (BO) and propose a novel approach referred to as Pareto front-Diverse Batch Multi-Objective BO (PDBO). PDBO tackles two important challenges: 1) How to automatically select the best acquisition function in each BO iteration, and 2) How to select a diverse batch of inputs by considering multiple objectives. We propose principled solutions to address these two challenges. First, PDBO employs a multi-armed bandit approach to select one acquisition function from a given library. We solve a cheap MOO problem by assigning the selected acquisition function for each expensive objective function to obtain a candidate set of inputs for evaluation. Second, it utilizes Determinantal Point Processes (DPPs) to choose a Pareto-front-diverse batch of inputs for evaluation from the candidate set obtained from the first step. The key parameters for the methods behind these two steps are updated after each round of function evaluations. Experiments on multiple MOO benchmarks demonstrate that PDBO outperforms prior methods in terms of both the quality and diversity of Pareto solutions., Comment: Published at AAAI Conference on Artificial Intelligence, 2024

Conformal prediction (CP) is an emerging uncertainty quantification framework that allows us to construct a prediction set to cover the true label with a pre-specified marginal or conditional probability. Although the valid coverage guarantee has been extensively studied for classification problems, CP often produces large prediction sets which may not be practically useful. This issue is exacerbated for the setting of class-conditional coverage on imbalanced classification tasks with many and/or imbalanced classes. This paper proposes the Rank Calibrated Class-conditional CP (RC3P) algorithm to reduce the prediction set sizes to achieve class-conditional coverage, where the valid coverage holds for each class. In contrast to the standard class-conditional CP (CCP) method that uniformly thresholds the class-wise conformity score for each class, the augmented label rank calibration step allows RC3P to selectively iterate this class-wise thresholding subroutine only for a subset of classes whose class-wise top-k error is small. We prove that agnostic to the classifier and data distribution, RC3P achieves class-wise coverage. We also show that RC3P reduces the size of prediction sets compared to the CCP method. Comprehensive experiments on multiple real-world datasets demonstrate that RC3P achieves class-wise coverage and 26.25% reduction in prediction set sizes on average.

Traditional digital implementations of neural accelerators are limited by high power and area overheads, while analog and non-CMOS implementations suffer from noise, device mismatch, and reliability issues. This paper introduces a CMOS Look-Up Table (LUT)-based Neural Accelerator (LUT-NA) framework that reduces the power, latency, and area consumption of traditional digital accelerators through pre-computed, faster look-ups while avoiding noise and mismatch of analog circuits. To solve the scalability issues of conventional LUT-based computation, we split the high-precision multiply and accumulate (MAC) operations into lower-precision MACs using a divide-and-conquer-based approach. We show that LUT-NA achieves up to $29.54\times$ lower area with $3.34\times$ lower energy per inference task than traditional LUT-based techniques and up to $1.23\times$ lower area with $1.80\times$ lower energy per inference task than conventional digital MAC-based techniques (Wallace Tree/Array Multipliers) without retraining and without affecting accuracy, even on lottery ticket pruned (LTP) models that already reduce the number of required MAC operations by up to 98%. Finally, we introduce mixed precision analysis in LUT-NA framework for various LTP models (VGG11, VGG19, Resnet18, Resnet34, GoogleNet) that achieved up to $32.22\times$-$50.95\times$ lower area across models with $3.68\times$-$6.25\times$ lower energy per inference than traditional LUT-based techniques, and up to $1.35\times$-$2.14\times$ lower area requirement with $1.99\times$-$3.38\times$ lower energy per inference across models as compared to conventional digital MAC-based techniques with $\sim$1% accuracy loss., Comment: 7 pages

Predicting the spatiotemporal variation in streamflow along with uncertainty quantification enables decision-making for sustainable management of scarce water resources. Process-based hydrological models (aka physics-based models) are based on physical laws, but using simplifying assumptions which can lead to poor accuracy. Data-driven approaches offer a powerful alternative, but they require large amount of training data and tend to produce predictions that are inconsistent with physical laws. This paper studies a constrained reasoning and learning (CRL) approach where physical laws represented as logical constraints are integrated as a layer in the deep neural network. To address small data setting, we develop a theoretically-grounded training approach to improve the generalization accuracy of deep models. For uncertainty quantification, we combine the synergistic strengths of Gaussian processes (GPs) and deep temporal models (i.e., deep models for time-series forecasting) by passing the learned latent representation as input to a standard distance-based kernel. Experiments on multiple real-world datasets demonstrate the effectiveness of both CRL and GP with deep kernel approaches over strong baseline methods.

Offline optimization is an emerging problem in many experimental engineering domains including protein, drug or aircraft design, where online experimentation to collect evaluation data is too expensive or dangerous. To avoid that, one has to optimize an unknown function given only its offline evaluation at a fixed set of inputs. A naive solution to this problem is to learn a surrogate model of the unknown function and optimize this surrogate instead. However, such a naive optimizer is prone to erroneous overestimation of the surrogate (possibly due to over-fitting on a biased sample of function evaluation) on inputs outside the offline dataset. Prior approaches addressing this challenge have primarily focused on learning robust surrogate models. However, their search strategies are derived from the surrogate model rather than the actual offline data. To fill this important gap, we introduce a new learning-to-search perspective for offline optimization by reformulating it as an offline reinforcement learning problem. Our proposed policy-guided gradient search approach explicitly learns the best policy for a given surrogate model created from the offline data. Our empirical results on multiple benchmarks demonstrate that the learned optimization policy can be combined with existing offline surrogates to significantly improve the optimization performance., Comment: Published at AAAI Conference on Artificial Intelligence, 2024

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 model parallel scenarios, latter being addressed for the first time. The search optimized accelerators for training relevant metrics such as throughput/TDP under a fixed area and power constraints. However, with the proliferation of specialized architectures and complex distributed training mechanisms, the design space exploration of hardware accelerators is very large. Prior work in this space has tried to tackle this by reducing the search space to either a single accelerator execution that too only for inference, or tuning the architecture for specific layers (e.g., convolution). Instead, we take a unique heuristic-based critical path-based approach to determine the best use of available resources (power and area) either for a set of DNN workloads or each workload individually. First, we perform local search to determine the architecture for each pipeline and tensor model stage. Specifically, the system iteratively generates architectural configurations and tunes the design using a novel heuristic-based approach that prioritizes accelerator resources and scheduling to critical operators in a machine learning workload. Second, to address the complexities of distributed training, the local search selects multiple (k) designs per stage. A global search then identifies an accelerator from the top-k sets to optimize training throughput across the stages. We evaluate this work on 11 different DNN models. Compared to a recent inference-only work Spotlight, our method converges to a design in, on average, 31x less time and offers 12x higher throughput. Moreover, designs generated using our method achieve 12% throughput improvement over TPU architecture.

Processing-in-memory (PIM) has emerged as an enabler for the energy-efficient and high-performance acceleration of deep learning (DL) workloads. Resistive random-access memory (ReRAM) is one of the most promising technologies to implement PIM. However, as the complexity of Deep convolutional neural networks (DNNs) grows, we need to design a manycore architecture with multiple ReRAM-based processing elements (PEs) on a single chip. Existing PIM-based architectures mostly focus on computation while ignoring the role of communication. ReRAM-based tiled manycore architectures often involve many Processing Elements (PEs), which need to be interconnected via an efficient on-chip communication infrastructure. Simply allocating more resources (ReRAMs) to speed up only computation is ineffective if the communication infrastructure cannot keep up with it. In this paper, we highlight the design principles of a dataflow-aware PIM-enabled manycore platform tailor-made for various types of DL workloads. We consider the design challenges with both 2.5D interposer- and 3D integration-enabled architectures., Comment: Presented at DATE Conference, Valencia, Spain 2024

This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As Large Language Models (LLMs) scale to billions of parameters, leveraging expansive datasets, they exhibit enhanced linguistic capabilities and emergent abilities. However, this growth raises significant computational and privacy concerns. Our study addresses these issues by exploring the potential of MoE models, known for their computational efficiency, and the application of DP, a standard for privacy preservation. We present the first known attempt to train MoE models under the constraints of DP, addressing the unique challenges posed by their architecture and the complexities of DP integration. Our initial experimental studies demonstrate that MoE models can be effectively trained with DP, achieving performance that is competitive with their non-private counterparts. This initial study aims to provide valuable insights and ignite further research in the domain of privacy-preserving MoE models, softly laying the groundwork for prospective developments in this evolving field., Comment: Preliminary work presented as a poster at the 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI 24)

We present a study of three highly non-radial solar wind events when the azimuthal solar wind flow angle exceeds > 6 degrees for one day or more. None of the events are associated with coronal mass ejections and co-rotating interaction regions observed at 1 AU. For all events, the solar wind outflows at 1 AU have low solar wind velocity and solar wind density. Based on the significant increase in the Oxygen charge state ratio of O7+/O6+ at 1 AU for all of the events, we have traced them back to the Sun and found that their source regions originated in an active region and coronal hole (AR-CH) pairs mainly located at the central meridian. Further, examining the dynamical evolutions in their source regions using both the Extreme ultra-violet Imaging Telescope and Michelson Doppler Imager, it is found that the changes taking place in AR-CH boundaries eventually disturbed the stable CH configurations, resulting in a reduction of the CH area and finally its disappearance, leaving only with the AR. Our study provides a possible explanation to discuss the origin of the prolonged and highly non-radial solar wind flows., Comment: Bulletin de la Soci\'et\'e Royale des Sciences de Li\`ege (BSRSL), 93 (2), 1-13 (in press)

Resistive random-access memory (ReRAM)-based processing-in-memory (PIM) architecture is an attractive solution for training Graph Neural Networks (GNNs) on edge platforms. However, the immature fabrication process and limited write endurance of ReRAMs make them prone to hardware faults, thereby limiting their widespread adoption for GNN training. Further, the existing fault-tolerant solutions prove inadequate for effectively training GNNs in the presence of faults. In this paper, we propose a fault-aware framework referred to as FARe that mitigates the effect of faults during GNN training. FARe outperforms existing approaches in terms of both accuracy and timing overhead. Experimental results demonstrate that FARe framework can restore GNN test accuracy by 47.6% on faulty ReRAM hardware with a ~1% timing overhead compared to the fault-free counterpart., Comment: This paper has been accepted to the conference DATE (Design, Automation and Test in Europe) - 2024

Transformers have revolutionized deep learning and generative modeling, enabling unprecedented advancements in natural language processing tasks. However, the size of transformer models is increasing continuously, driven by enhanced capabilities across various deep-learning tasks. This trend of ever-increasing model size has given rise to new challenges in terms of memory and computing requirements. Conventional computing platforms, including GPUs, suffer from suboptimal performance due to the memory demands imposed by models with millions/billions of parameters. The emerging chiplet-based platforms provide a new avenue for compute- and data-intensive machine learning (ML) applications enabled by a Network-on-Interposer (NoI). However, designing suitable hardware accelerators for executing Transformer inference workloads is challenging due to a wide variety of complex computing kernels in the Transformer architecture. In this paper, we leverage chiplet-based heterogeneous integration (HI) to design a high-performance and energy-efficient multi-chiplet platform to accelerate transformer workloads. We demonstrate that the proposed NoI architecture caters to the data access patterns inherent in a transformer model. The optimized placement of the chiplets and the associated NoI links and routers enable superior performance compared to the state-of-the-art hardware accelerators. The proposed NoI-based architecture demonstrates scalability across varying transformer models and improves latency and energy efficiency by up to 22.8x and 5.36x respectively., Comment: Preprint for a Heterogeneous Chiplet Architecture for Accelerating End-to-End Transformer Models

Small-scale models offer various computational advantages, and yet to which extent size is critical for problem-solving abilities remains an open question. Specifically for solving grade school math, the smallest model size so far required to break the 80\% barrier on the GSM8K benchmark remains to be 34B. Our work studies how high-quality datasets may be the key for small language models to acquire mathematical reasoning. We introduce \texttt{TinyGSM}, a synthetic dataset of 12.3M grade school math problems paired with Python solutions, generated fully by GPT-3.5. After finetuning on \texttt{TinyGSM}, we find that a duo of a 1.3B generation model and a 1.3B verifier model can achieve 81.5\% accuracy, outperforming existing models that are orders of magnitude larger. This also rivals the performance of the GPT-3.5 ``teacher'' model (77.4\%), from which our model's training data is generated. Our approach is simple and has two key components: 1) the high-quality dataset \texttt{TinyGSM}, 2) the use of a verifier, which selects the final outputs from multiple candidate generations.

In this paper, we consider differentially private classification when some features are sensitive, while the rest of the features and the label are not. We adapt the definition of differential privacy naturally to this setting. Our main contribution is a novel adaptation of AdaBoost that is not only provably differentially private, but also significantly outperforms a natural benchmark that assumes the entire data of the individual is sensitive in the experiments. As a surprising observation, we show that boosting randomly generated classifiers suffices to achieve high accuracy. Our approach easily adapts to the classical setting where all the features are sensitive, providing an alternate algorithm for differentially private linear classification with a much simpler privacy proof and comparable or higher accuracy than differentially private logistic regression on real-world datasets.

Advancement in the field of machine learning is unavoidable, but something of major concern is preserving the privacy of the users whose data is being used for training these machine learning algorithms. Federated learning(FL) has emerged as a promising paradigm for training machine learning models in a distributed and privacy-preserving manner which enables one to collaborate and train a global model without sharing local data. But starting this learning process on each device in the right way, called ``model initialization" is critical. The choice of initialization methods used for models plays a crucial role in the performance, convergence speed, communication efficiency, privacy guarantees of federated learning systems, etc. In this survey, we dive deeper into a comprehensive study of various ways of model initialization techniques in FL.Unlike other studies, our research meticulously compares, categorizes, and delineates the merits and demerits of each technique, examining their applicability across diverse FL scenarios. We highlight how factors like client variability, data non-IIDness, model caliber, security considerations, and network restrictions influence FL model outcomes and propose how strategic initialization can address and potentially rectify many such challenges. The motivation behind this survey is to highlight that the right start can help overcome challenges like varying data quality, security issues, and network problems. Our insights provide a foundational base for experts looking to fully utilize FL, also while understanding the complexities of model initialization., Comment: Accepted to be presented at IEEE 2nd International Conference on Intelligent Computing and Next Generation Networks (ICNGN2023) will be held November 17-18,2023 at Hangzhou, China

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we initiate the study of privacy-preserving alignment of LLMs through Differential Privacy (DP) in conjunction with RL. Following the influential work of Ziegler et al. (2020), we study two dominant paradigms: (i) alignment via RL without human in the loop (e.g., positive review generation) and (ii) alignment via RL from human feedback (RLHF) (e.g., summarization in a human-preferred way). We give a new DP framework to achieve alignment via RL, and prove its correctness. Our experimental results validate the effectiveness of our approach, offering competitive utility while ensuring strong privacy protections., Comment: Accepted at ICLR 2024

Large language models have revolutionized the field of NLP by achieving state-of-the-art performance on various tasks. However, there is a concern that these models may disclose information in the training data. In this study, we focus on the summarization task and investigate the membership inference (MI) attack: given a sample and black-box access to a model's API, it is possible to determine if the sample was part of the training data. We exploit text similarity and the model's resistance to document modifications as potential MI signals and evaluate their effectiveness on widely used datasets. Our results demonstrate that summarization models are at risk of exposing data membership, even in cases where the reference summary is not available. Furthermore, we discuss several safeguards for training summarization models to protect against MI attacks and discuss the inherent trade-off between privacy and utility.

Resistive random access memory (ReRAM)-based processing-in-memory (PIM) architectures have demonstrated great potential to accelerate Deep Neural Network (DNN) training/inference. However, the computational accuracy of analog PIM is compromised due to the non-idealities, such as the conductance variation of ReRAM cells. The impact of these non-idealities worsens as the number of concurrently activated wordlines and bitlines increases. To guarantee computational accuracy, only a limited number of wordlines and bitlines of the crossbar array can be turned on concurrently, significantly reducing the achievable parallelism of the architecture. While the constraints on parallelism limit the efficiency of the accelerators, they also provide a new opportunity for fine-grained mixed-precision quantization. To enable efficient DNN inference on practical ReRAM-based accelerators, we propose an algorithm-architecture co-design framework called \underline{B}lock-\underline{W}ise mixed-precision \underline{Q}uantization (BWQ). At the algorithm level, BWQ-A introduces a mixed-precision quantization scheme at the block level, which achieves a high weight and activation compression ratio with negligible accuracy degradation. We also present the hardware architecture design BWQ-H, which leverages the low-bit-width models achieved by BWQ-A to perform high-efficiency DNN inference on ReRAM devices. BWQ-H also adopts a novel precision-aware weight mapping method to increase the ReRAM crossbar's throughput. Our evaluation demonstrates the effectiveness of BWQ, which achieves a 6.08x speedup and a 17.47x energy saving on average compared to existing ReRAM-based architectures., Comment: 12 pages, 13 figures

We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel algorithm that generates synthetic few-shot demonstrations from the private dataset with formal differential privacy (DP) guarantees, and show empirically that it can achieve effective ICL. We conduct extensive experiments on standard benchmarks and compare our algorithm with non-private ICL and zero-shot solutions. Our results demonstrate that our algorithm can achieve competitive performance with strong privacy levels. These results open up new possibilities for ICL with privacy protection for a broad range of applications.

Processing visual data on mobile devices has many applications, e.g., emergency response and tracking. State-of-the-art computer vision techniques rely on large Deep Neural Networks (DNNs) that are usually too power-hungry to be deployed on resource-constrained edge devices. Many techniques improve the efficiency of DNNs by using sparsity or quantization. However, the accuracy and efficiency of these techniques cannot be adapted for diverse edge applications with different hardware constraints and accuracy requirements. This paper presents a novel technique to allow DNNs to adapt their accuracy and energy consumption during run-time, without the need for any re-training. Our technique called AdaptiveActivation introduces a hyper-parameter that controls the output range of the DNNs' activation function to dynamically adjust the sparsity and precision in the DNN. AdaptiveActivation can be applied to any existing pre-trained DNN to improve their deployability in diverse edge environments. We conduct experiments on popular edge devices and show that the accuracy is within 1.5% of the baseline. We also show that our approach requires 10%--38% less memory than the baseline techniques leading to more accuracy-efficiency tradeoff options

The IoT ecosystem is able to leverage vast amounts of data for intelligent decision-making. Federated Learning (FL), a decentralized machine learning technique, is widely used to collect and train machine learning models from a variety of distributed data sources. Both IoT and FL systems can be complementary and used together. However, the resource-constrained nature of IoT devices prevents the widescale deployment FL in the real world. This research paper presents a comprehensive survey of the challenges and solutions associated with implementing Federated Learning (FL) in resource-constrained Internet of Things (IoT) environments, viewed from 2 levels, client and server. We focus on solutions regarding limited client resources, presence of heterogeneous client data, server capacity, and high communication costs, and assess their effectiveness in various scenarios. Furthermore, we categorize the solutions based on the location of their application, i.e., the IoT client, and the FL server. In addition to a comprehensive review of existing research and potential future directions, this paper also presents new evaluation metrics that would allow researchers to evaluate their solutions on resource-constrained IoT devices., Comment: Presented and accepted at The IEEE 2023 International Conference on Artificial Intelligence, Robotics, Signal and Image Processing (AIRoSIP)

We prove that there exists an online algorithm that for any sequence of vectors $v_1,\ldots,v_T \in \mathbb{R}^n$ with $\|v_i\|_2 \leq 1$, arriving one at a time, decides random signs $x_1,\ldots,x_T \in \{ -1,1\}$ so that for every $t \le T$, the prefix sum $\sum_{i=1}^t x_iv_i$ is $10$-subgaussian. This improves over the work of Alweiss, Liu and Sawhney who kept prefix sums $O(\sqrt{\log (nT)})$-subgaussian, and gives a $O(\sqrt{\log T})$ bound on the discrepancy $\max_{t \in T} \|\sum_{i=1}^t x_i v_i\|_\infty$. Our proof combines a generalization of Banaszczyk's prefix balancing result to trees with a cloning argument to find distributions rather than single colorings. We also show a matching $\Omega(\sqrt{\log T})$ strategy for an oblivious adversary., Comment: 22 pages

Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deploy on small battery-powered Internet-of-Things (IoT) devices with limited computing resources. Deployment of DNNs on Internet-of-Things devices, such as traffic cameras, can improve public safety by enabling applications such as automatic accident detection and emergency response.Through this paper, we survey the recent advances in low-power and energy-efficient DNN implementations that improve the deployability of DNNs without significantly sacrificing accuracy. In general, these techniques either reduce the memory requirements, the number of arithmetic operations, or both. The techniques can be divided into three major categories: neural network compression, network architecture search and design, and compiler and graph optimizations. In this paper, we survey both low-power techniques for both convolutional and transformer DNNs, and summarize the advantages, disadvantages, and open research problems., Comment: Accepted and presented at THE IEEE INTERNATIONAL CONFERENCE ON INDUSTRY 4.0, ARTIFICIAL INTELLIGENCE, AND COMMUNICATIONS TECHNOLOGY