Method predicts hardware resource usage by control software with guaranteed linear convergence.
problem Predicting time-varying hardware resource availability in control software.
method Path structured multimarginal Schrödinger bridge (MSBP) for learning stochastic resource usage.
result Guaranteed linear convergence to accurate prediction of hardware resource utilization.
ALF reduces network parameters and operations by 70% and 61%, respectively, on embedded hardware.
problem Efficient deployment of deep learning models on resource-constrained hardware.
method Autoencoder-based low-rank filter-sharing technique.
result ALF achieves significant compression with minimal accuracy loss.
Paper presents efficient algorithms for convolutional neural networks using Winograd minimal filtering.
problem Resource-efficient implementation of convolutional neural networks.
method Winograd minimal filtering trick applied to M-tap filters (M=3,5,7,9,11) for parallel hardware implementation.
result Approximately 30% reduction in multipliers for fully parallel hardware implementation.
Improves VQAs by balancing classical and quantum training resources.
problem Challenges in trainability and resource costs of VQAs on quantum hardware.
method Adopting HELIA Ansatz and combining classical and quantum methods for gradient estimation and training.
result Achieves higher accuracy and success rates in VQE and improved test accuracy in quantum phase classification.
Paper proposes efficient INT4 quantization for neural networks.
problem Efficient inference on limited hardware resources for large neural networks.
method Formalizes quantization as MMSE problem, optimizes constrained MSE at each layer, partitions parameters, uses multiple quantized tensors.
result 4-bit integer (INT4) quantization yields state-of-the-art results with minimal accuracy loss.
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural networks (DNNs). An algorithm-hardware co-optimization framework is developed, which i…
TinyCNN accelerates CNN models on embedded FPGA with 15x speedup.
problem Limited memory on embedded FPGAs restricts CNN performance.
method Software and hardware design tool for FPGA resource-aware CNN accelerator.
result 3% accuracy loss with 15.75x speedup on image classification.
A new framework for coreset selection in machine learning models.
problem Learning models under resource constraints.
method Formulates coreset selection as a bilevel optimization problem.
result Framework applies to any twice differentiable model, including neural networks.
This paper optimizes deep neural networks for resource-constrained devices.
problem Efficient deployment of deep neural networks on resource-constrained devices.
method Across-stack optimization of CNNs using weight pruning, channel pruning, quantization, and parallel execution.
result Comprehensive Pareto curves for trade-offs between accuracy, execution time, and memory space.
Review of efficient neural networks for TinyML on resource-constrained devices.
problem Resource constraints on ultra-low power MCUs for deep learning models.
method Model compression, quantization, low-rank factorization, model pruning, hardware acceleration, algorithm-architecture co-design.
result Optimized neural network architectures for minimal resource utilization on MCUs.
Regularizes decision trees to reduce inference time by up to 4x with minimal accuracy loss.
problem Optimizing decision tree execution time on resource-constrained devices.
method Regularizes impurity computation during CART algorithm training to favor highly asymmetric distributions.
result Reduces inference time by up to 4x with minimal accuracy loss.
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.
problem Efficient deep learning inference on resource-constrained hardware.
method Joint optimization of neural architecture, pruning, and quantization policy using a quantization-aware accuracy predictor.
result Joint optimization leads to 2.3% higher ImageNet accuracy with reduced latency and energy consumption.
A framework for efficient multi-objective optimization using entropy search.
problem Optimizing expensive black-box functions with multiple objectives.
method Output space entropy search (OSE) to minimize resource cost.
result Improves efficiency and accuracy in multi-objective optimization.
Stealthy hardware Trojan exploits DLA architecture vulnerabilities.
problem Security of DLA deployed on hardware accelerators.
method Input Interception Attack (IIA) exploiting statistical properties of DLA outputs.
result Stealthy Trojan can trigger with some definiteness.
A new optimizer saves significant shots in quantum machine learning.
problem Training variational QML algorithms is challenging due to large datasets and shot-count overhead.
method Proposed Refoqus optimizer that samples over both dataset and measurement operators.
result Refoqus can save several orders of magnitude in shot cost compared to existing methods.
New method improves neural architecture search by optimizing for both performance and diversity.
problem Traditional multi-objective NAS fails to address practical constraints and niches.
method Formulated as quality diversity optimization, introduces multifidelity optimizers.
result Quality diversity NAS outperforms multi-objective NAS in quality and efficiency.
This paper proposes a method to automatically compress neural networks using Bayesian tensor decomposition.
problem Challenges in directly applying tensor compression in neural network training.
method Bayesian tensorized neural network with automatic rank selection.
result Produces significantly more compact neural networks (7.4x to 137x) directly from training.
Generative profiling improves real-time task timing for varied resource contexts.
problem Inaccurate task timing analysis for complex hardware architectures.
method Nonparametric, conditional multi-marginal Schrödinger Bridge (MSB) formulation for synthesizing context-dependent timing profiles.
result Maximum likelihood accurate execution profiles for unseen resource contexts.
Binary and ternary weights simplify RNNs for mobile devices.
problem Complexity and memory intensity of RNNs on mobile devices.
method Learn binary and ternary weights during training.
result Significant memory saving and inference speedup on ASIC platform.
Resource-efficient oblique trees reduce neural signal classification costs.
problem Implementing efficient neural signal classifiers on resource-constrained devices.
method Integrating model compression, probabilistic routing, and cost-aware learning.
result Significant reduction in model size and feature extraction cost compared to state-of-the-art models.
New algorithm generates diverse sparse neural network topologies.
problem Training deep neural networks requires significant hardware resources.
method Deterministic algorithm to generate sparse neural network topologies.
result Generated topologies train to the same precision as dense DNNs at lower cost.
TonY simplifies distributed ML job management.
problem Managing distributed ML jobs is complex and resource-intensive.
method TonY is an open-source orchestrator for distributed ML jobs.
result TonY simplifies distributed ML job management.
ESAC combines genetic methods with RL to improve scalability and efficiency.
problem Combining genetic scalability with RL's data efficiency and optimal control.
method Combines Evolution Strategies (ES) with Soft Actor-Critic (SAC) to enable skill transfer and reduce hyperparameter sensitivity.
result Demonstrates improved performance and sample efficiency in challenging tasks.
ECC compresses DNNs for energy-constrained devices like UAVs and smartphones.
problem Energy-constrained deep neural networks in vision applications.
method ECC uses a bilinear regression model to estimate DNN energy consumption and optimizes compression to meet energy constraints.
result ECC achieves higher accuracy under the same or lower energy budget compared to state-of-the-art techniques.
Developing active inference agents for edge devices with limited resources.
problem Creating effective active inference agents on edge devices with limited computational resources.
method Introducing a software toolbox to accelerate the development of active inference agents by non-experts.
result Accelerates the democratization of active inference agents for edge devices.
Real-time semantic segmentation for autonomous vehicles on FPGA reduces latency and power consumption.
problem Efficient real-time semantic segmentation for autonomous vehicles.
method Compressed ENet architecture, FPGA deployment, batch processing, filter reduction, quantization-aware training.
result Reduced latency to 3 ms per image with batch size of ten and 40% resource utilization.
CLEANN detects and mitigates neural network Trojans without labeled data.
problem Trojans in embedded neural networks that bypass detection during inference.
method Dictionary learning and sparse approximation for identifying Trojan triggers, lightweight algorithm/hardware co-design.
result Efficient real-time execution on resource-constrained platforms, competitive attack resiliency.
New asynchronous SGD algorithms achieve optimal performance in distributed learning.
problem Asynchronous training introduces staleness, complicating optimization analysis.
method Developed rigorous framework for asynchronous first order stochastic optimization.
result Asynchronous SGD can achieve optimal time complexity, matching synchronous methods.
The paper tackles hardware efficiency in DL models, predicting and optimizing for latency and energy cost.
problem Predicting and optimizing hardware efficiency for DL models during inference.
method Develops predictive models and hardware-aware optimization techniques.
result Predictive models and optimization techniques can significantly improve hardware efficiency in DL applications.
Quantum advantage in derivative pricing requires 8k qubits and 54M T-depth.
problem Quantum advantage in pricing derivatives.
method Re-parameterization method combining pre-trained variational circuits and fault-tolerant quantum computing.
result Benchmark use cases require 8k logical qubits and a T-depth of 54 million.
Automated design of resilient, efficient DNNs for hardware.
problem Designing reliable and efficient DNNs for hardware.
method Evolutionary optimization technique for DNN architecture design.
result Strong correlation between predicted and actual error resilience.
FrostNet improves INT8 quantization efficiency in mobile networks.
problem The importance of network architecture for optimal INT8 quantization.
method Quantization-aware training (QAT) with StatAssist and GradBoost, hardware-aware NAS.
result FrostNets achieve higher recognition accuracy with comparable latency when quantized.
Efficient FPGA dropout algorithm reduces memory usage.
problem Overfitting in deep neural networks.
method Hardware-oriented dropout algorithm for FPGA implementation.
result Significant resource reduction in FPGA implementation.
PABO optimizes DNN and hardware hyperparameters for efficient edge device acceleration.
problem Joint optimization of DNN accuracy and hardware cost for edge devices.
method Bayesian optimization with pseudo agent-based approach for memristive crossbar accelerators.
result PABO achieves significant speed-ups and superior performance compared to state-of-the-art methods.
RiskNet predicts penalties in unreliable communication networks using GNNs.
problem Predicting penalties in networks with unreliable resources.
method Graph Neural Network (GNN) based approach trained on random graphs.
result Precisely models penalties across various network topologies.
New Ising models improve consensus clustering on specialized hardware.
problem Consensus clustering optimization problems.
method Formulated consensus clustering as Ising models and evaluated on specialized hardware.
result Our Ising models outperform existing techniques on consensus clustering.
Quantum algorithms for CVaR portfolio optimization face trade-offs between hardware coherence and expressibility.
problem Quantum algorithmic resilience for CVaR portfolio optimization
method WS-QAOA vs. HE-VQNN
result WS-QAOA provides exact theoretical mapping but suffers from hardware decoherence, while HE-VQNN preserves hardware coherence but lacks expressibility.
We derive scaling laws for optimizing neural networks in hardware.
problem Optimizing the large parameter space of neural networks in hardware.
method Analytical derivation of scaling laws for Coordinate Descent optimization.
result Convergence is exponential and scales linearly with the number of neurons.
Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we present a large batch, stochastic optimization algorithm that is both faster tha…
This paper tackles co-design of neural hardware and software to improve efficiency.
problem Designing efficient deep learning systems that consider both hardware and software optimizations together.
method Developed a constrained Bayesian optimization framework to automatically identify profitable design points in the joint hardware/software design space.
result Improved energy-delay product by 18% (ResNet) and 40% (DQN) over hand-tuned systems.
Novel approach reduces DNN redundancy and enhances computational efficiency.
problem Redundant parameters in large-scale DNNs pose hardware deployment challenges.
method WGSEF regularization technique for structured sparsity.
result Reduces redundancy and enhances computational efficiency.
DANCE optimizes neural network and accelerator design for faster, more efficient DNN execution.
problem Challenges in optimizing neural network and accelerator design for efficient DNN execution.
method Differentiable approach to co-exploration of accelerator and network architecture design.
result Significantly shorter time to achieve superior accuracy and hardware cost metrics.
Gradient-free deep learning for large datasets.
problem Training deep neural networks on large-scale datasets is resource-intensive and requires specialized techniques.
method Recursive Local Representation Alignment (RLRA) for gradient-free training.
result RLRA achieves comparable performance to backprop while converging faster and being parallelizable.
Quantum circuits explained using Shapley values for better understanding.
problem Improving the explainability of quantum machine learning circuits.
method Applying Shapley values to quantify gate importance in quantum circuits.
result Quantum circuits can be explained by their gate importance, enhancing understanding and interpretability.
Efficient neural networks for resource-constrained systems.
problem Reducing resource consumption in machine learning models for embedded systems.
method Quantized neural networks, network pruning, structural efficiency.
result Finding good trade-offs between resource efficiency and prediction quality is challenging.
New neuromorphic hardware learns MNIST digits efficiently.
problem Limited scalability and in-hardware learning in existing neuromorphic hardware.
method Low-cost scalable NoC-based SNN architecture with in-hardware STDP learning.
result Demonstrated learning capability of the hardware architecture.
SmartDeal reduces energy and storage costs for deep neural networks.
problem Heavy parameterization of deep neural networks leads to inefficient use of DRAM.
method SmartDeal decomposes weights into a small basis matrix and a structurally sparse coefficient matrix, quantized to power-of-2.
result Up to 2.44x energy efficiency improvement in inference and 10.56x reduction in training energy.
Paper proposes efficient BNN inference flow to reduce computation and memory costs.
problem High computation complexity in Bayesian Neural Networks (BNNs) limits deployment in power-constrained systems.
method Feature decomposition and memorization strategy to reduce computations and a memory-friendly computing framework to reduce memory overhead.
result Reduces computation by about half and energy consumption by 73% with 14% area overhead.