arXiv subjects

Bill Lin

Publications and source records attributed to Bill Lin.

27 records · Page 2Linked to original sources

arXiv2022

NeuCASL: From Logic Design to System Simulation of Neuromorphic Engines

With Moore's law saturating and Dennard scaling hitting its wall, traditional Von Neuman systems cannot offer the GFlops/watt for compute-intensive algorithms such as CNN. Recent trends in unconventional computing approaches give us hope to design highly energy-efficient computing systems for such algorithms. Neuromorphic computing is a promising such approach with its brain-inspired circuitry, use of emerging technologies, and low-power nature. Researchers use a variety of novel technologies such as memristors, silicon photonics, FinFET, and carbon nanotubes to demonstrate a neuromorphic computer. However, a flexible CAD tool to start from neuromorphic logic design and go up to architectural simulation is yet to be demonstrated to support the rise of this promising paradigm. In this project, we aim to build NeuCASL, an opensource python-based full system CAD framework for neuromorphic logic design, circuit simulation, and system performance and reliability estimation. This is a first of its kind to the best of our knowledge.

cs.ET↗

arXiv2022

LiteCON: An All-Photonic Neuromorphic Accelerator for Energy-efficient Deep Learning (Preprint)

Deep learning is highly pervasive in today's data-intensive era. In particular, convolutional neural networks (CNNs) are being widely adopted in a variety of fields for superior accuracy. However, computing deep CNNs on traditional CPUs and GPUs brings several performance and energy pitfalls. Several novel approaches based on ASIC, FPGA, and resistive-memory devices have been recently demonstrated with promising results. Most of them target only the inference (testing) phase of deep learning. There have been very limited attempts to design a full-fledged deep learning accelerator capable of both training and inference. It is due to the highly compute and memory-intensive nature of the training phase. In this paper, we propose LiteCON, a novel analog photonics CNN accelerator. LiteCON uses silicon microdisk-based convolution, memristor-based memory, and dense-wavelength-division-multiplexing for energy-efficient and ultrafast deep learning. We evaluate LiteCON using a commercial CAD framework (IPKISS) on deep learning benchmark models including LeNet and VGG-Net. Compared to the state-of-the-art, LiteCON improves the CNN throughput, energy efficiency, and computational efficiency by up to 32x, 37x, and 5x respectively with trivial accuracy degradation.

cs.ET↗

arXiv2021

Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity

The traditional approach in FL tries to learn a single global model collaboratively with the help of many clients under the orchestration of a central server. However, learning a single global model might not work well for all clients participating in the FL under data heterogeneity. Therefore, the personalization of the global model becomes crucial in handling the challenges that arise with statistical heterogeneity and the non-IID distribution of data. Unlike prior works, in this work we propose a new approach for obtaining a personalized model from a client-level objective. This further motivates all clients to participate in federation even under statistical heterogeneity in order to improve their performance, instead of merely being a source of data and model training for the central server. To realize this personalization, we leverage finding a small subnetwork for each client by applying hybrid pruning (combination of structured and unstructured pruning), and unstructured pruning. Through a range of experiments on different benchmarks, we observed that the clients with similar data (labels) share similar personal parameters. By finding a subnetwork for each client ...

cs.LG↗

arXiv2021

Learning Accurate and Interpretable Decision Rule Sets from Neural Networks

This paper proposes a new paradigm for learning a set of independent logical rules in disjunctive normal form as an interpretable model for classification. We consider the problem of learning an interpretable decision rule set as training a neural network in a specific, yet very simple two-layer architecture. Each neuron in the first layer directly maps to an interpretable if-then rule after training, and the output neuron in the second layer directly maps to a disjunction of the first-layer rules to form the decision rule set. Our representation of neurons in this first rules layer enables us to encode both the positive and the negative association of features in a decision rule. State-of-the-art neural net training approaches can be leveraged for learning highly accurate classification models. Moreover, we propose a sparsity-based regularization approach to balance between classification accuracy and the simplicity of the derived rules. Our experimental results show that our method can generate more accurate decision rule sets than other state-of-the-art rule-learning algorithms with better accuracy-simplicity trade-offs. Further, when compared with uninterpretable black-box machine learning approaches such as random forests and full-precision deep neural networks, our approach can easily find interpretable decision rule sets that have comparable predictive performance.

cs.LG↗

arXiv2020

Differentially-private Federated Neural Architecture Search

Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress recently. In many application scenarios, several parties would like to collaboratively search for a shared neural architecture by leveraging data from all parties. However, due to privacy concerns, no party wants its data to be seen by other parties. To address this problem, we propose federated neural architecture search (FNAS), where different parties collectively search for a differentiable architecture by exchanging gradients of architecture variables without exposing their data to other parties. To further preserve privacy, we study differentially-private FNAS (DP-FNAS), which adds random noise to the gradients of architecture variables. We provide theoretical guarantees of DP-FNAS in achieving differential privacy. Experiments show that DP-FNAS can search highly-performant neural architectures while protecting the privacy of individual parties. The code is available at https://github.com/UCSD-AI4H/DP-FNAS

cs.LG↗

arXiv2020

Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models

Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, clustering and augmentation are domain-dependent, and thus they require either manual tweaking or expensive learning. In this work, we describe an approach that generates meta-tasks using generative models. A critical component is a novel approach of sampling from the latent space that generates objects grouped into synthetic classes forming the training and validation data of a meta-task. We find that the proposed approach, LAtent Space Interpolation Unsupervised Meta-learning (LASIUM), outperforms or is competitive with current unsupervised learning baselines on few-shot classification tasks on the most widely used benchmark datasets. In addition, the approach promises to be applicable without manual tweaking over a wider range of domains than previous approaches.

cs.LG↗

arXiv2019

Network Optimization for Unified Packet and Circuit Switched Networks

Internet traffic continues to grow relentlessly, driven largely by increasingly high resolution video content. Although studies have shown that the majority of packets processed by Internet routers are pass-through traffic, they nonetheless have to be queued and routed at every hop in current networks, which unnecessarily adds substantial delays and processing costs. Such pass-through traffic can be better circuit-switched through the underlying optical transport network by means of pre-established circuits, which is possible in a unified packet and circuit switched network. In this paper, we propose a novel convex optimization framework based on a new destination-based multicommodity flow formulation for the allocation of circuits in such unified networks. In particular, we consider two deployment settings, one based on real-time traffic monitoring, and the other relying upon history-based traffic predictions. In both cases, we formulate global network optimization objectives as concave functions that capture the fair sharing of network capacity among competing traffic flows. The convexity of our problem formulations ensures globally optimal solutions.

cs.NI↗

arXiv2018

SARA: Self-Aware Resource Allocation for Heterogeneous MPSoCs

In modern heterogeneous MPSoCs, the management of shared memory resources is crucial in delivering end-to-end QoS. Previous frameworks have either focused on singular QoS targets or the allocation of partitionable resources among CPU applications at relatively slow timescales. However, heterogeneous MPSoCs typically require instant response from the memory system where most resources cannot be partitioned. Moreover, the health of different cores in a heterogeneous MPSoC is often measured by diverse performance objectives. In this work, we propose a Self-Aware Resource Allocation (SARA) framework for heterogeneous MPSoCs. Priority-based adaptation allows cores to use different target performance and self-monitor their own intrinsic health. In response, the system allocates non-partitionable resources based on priorities. The proposed framework meets a diverse range of QoS demands from heterogeneous cores.

cs.DC↗

arXiv2014

Sprinklers: A Randomized Variable-Size Striping Approach to Reordering-Free Load-Balanced Switching

Internet traffic continues to grow exponentially, calling for switches that can scale well in both size and speed. While load-balanced switches can achieve such scalability, they suffer from a fundamental packet reordering problem. Existing proposals either suffer from poor worst-case packet delays or require sophisticated matching mechanisms. In this paper, we propose a new family of stable load-balanced switches called "Sprinklers" that has comparable implementation cost and performance as the baseline load-balanced switch, but yet can guarantee packet ordering. The main idea is to force all packets within the same virtual output queue (VOQ) to traverse the same "fat path" through the switch, so that packet reordering cannot occur. At the core of Sprinklers are two key innovations: a randomized way to determine the "fat path" for each VOQ, and a way to determine its "fatness" roughly in proportion to the rate of the VOQ. These innovations enable Sprinklers to achieve near-perfect load-balancing under arbitrary admissible traffic. Proving this property rigorously using novel worst-case large deviation techniques is another key contribution of this work.

cs.NI↗