A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Novel NAS method balances performance and hardware metrics efficiently.
Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a plethora of design challenges related to the constraints introduced by the hardware…
The thesis explores how to integrate machine learning with hardware constraints.
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture search (NAS) has revolutionized the design of hardware-efficient ConvNets by automating this process. However, the NAS problem remains challen…
A new penalty-free method optimizes portfolios without quantum annealing penalties.
Many DNN-enabled vision applications constantly operate under severe energy constraints such as unmanned aerial vehicles, Augmented Reality headsets, and smartphones. Designing DNNs that can meet a stringent energy budget is becoming increasingly important. This paper proposes ECC, a framework that compresses DNNs to m…
Convolutional neural networks (CNNs) demand huge DRAM bandwidth for computational imaging tasks, and block-based processing has recently been applied to greatly reduce the bandwidth. However, the induced additional computation for feature recomputing or the large SRAM for feature reusing will degrade the performance or…
CoCoPIE shows AI can run on regular devices without special hardware.
Game theory shows miners' hardware improvements don't centralize mining.
This paper proposes a hardware-oriented dropout algorithm, which is efficient for field programmable gate array (FPGA) implementation. In deep neural networks (DNNs), overfitting occurs when networks are overtrained and adapt too well to training data. Consequently, they fail in predicting unseen data used as test data…
HotNAS reduces AI search time from hundreds of GPU hours to less than 3 GPU hours.
New method for efficient sketching of gradients and Hessians.
Packed-Ensembles improve uncertainty estimation in constrained hardware.
Investigates ways to train larger models with fewer resources, finding that test loss depends only on the actual number of trainable parameters.
Quantum reservoir computing improves volatility forecasting.
Bayesian approach optimizes quantum circuits for noisy hardware.
Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without conne…
New method improves neural architecture search by optimizing for both performance and diversity.
PLUMAGE improves large model training efficiency and stability.
Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with limited computation and storage requires streamlined methodologies that can effi…
Bio-inspired neuromorphic hardware is a research direction to approach brain's computational power and energy efficiency. Spiking neural networks (SNN) encode information as sparsely distributed spike trains and employ spike-timing-dependent plasticity (STDP) mechanism for learning. Existing hardware implementations of…
On-device inference of machine learning models for mobile phones is desirable due to its lower latency and increased privacy. Running such a compute-intensive task solely on the mobile CPU, however, can be difficult due to limited computing power, thermal constraints, and energy consumption. App developers and research…
End-to-end portfolio optimization using quantum annealing for financial decision problems.
New KWS neural networks improve accuracy and power efficiency.
Deep learning architectures (DLA) have shown impressive performance in computer vision, natural language processing and so on. Many DLA make use of cloud computing to achieve classification due to the high computation and memory requirements. Privacy and latency concerns resulting from cloud computing has inspired the …
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
Quantum memory limits set by relativity theory.
Benchmark for DL inference on embedded HWAs, focusing on autonomous driving.
New Ising models improve consensus clustering on specialized hardware.
DANCE optimizes neural network and accelerator design for faster, more efficient DNN execution.
SmartDeal reduces energy and storage costs for deep neural networks.
We consider machine learning techniques to develop low-latency approximate solutions to a class of inverse problems. More precisely, we use a probabilistic approach for the problem of recovering sparse stochastic signals that are members of the -balls. In this context, we analyze the Bayesian mean-square-error …
In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot…
Paper tackles dynamic portfolio optimization using quantum and quantum-inspired methods.
Method predicts hardware resource usage by control software with guaranteed linear convergence.
Quantum algorithms for CVaR portfolio optimization face trade-offs between hardware coherence and expressibility.
We investigate the use of regularized Newton methods with adaptive norms for optimizing neural networks. This approach can be seen as a second-order counterpart of adaptive gradient methods, which we here show to be interpretable as first-order trust region methods with ellipsoidal constraints. In particular, we prove …
With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YO…
This paper tackles co-design of neural hardware and software to improve efficiency.
Telemonitoring of electroencephalogram (EEG) through wireless body-area networks is an evolving direction in personalized medicine. Among various constraints in designing such a system, three important constraints are energy consumption, data compression, and device cost. Conventional data compression methodologies, al…
2D-PT improves sampling in constrained optimization problems.
We derive scaling laws for optimizing neural networks in hardware.
New method bounds hardware noise without assumptions.
This paper highlights new opportunities for designing large-scale machine learning systems as a consequence of blurring traditional boundaries that have allowed algorithm designers and application-level practitioners to stay -- for the most part -- oblivious to the details of the underlying hardware-level implementatio…
Gaussian processes (GPs) are flexible non-parametric models, with a capacity that grows with the available data. However, computational constraints with standard inference procedures have limited exact GPs to problems with fewer than about ten thousand training points, necessitating approximations for larger datasets. …
Applying deep neural networks (DNNs) in mobile and safety-critical systems, such as autonomous vehicles, demands a reliable and efficient execution on hardware. Optimized dedicated hardware accelerators are being developed to achieve this. However, the design of efficient and reliable hardware has become increasingly d…
Study benchmarks methods for learning non-Cartesian k-space trajectories and reconstruction.
Optimized neural networks for Edge TPU achieve high accuracy in real-time image classification.