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.
Method predicts hardware resource usage by control software with guaranteed linear convergence.
Method learns software resource usage from snapshots.
Innovative neural networks reduce memory usage for efficient, accurate segmentation.
A new model improves homogeneity in burn patient reimbursement.
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
This study uses LSTM and SARIMA models to forecast CPU usage in cloud computing.
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…
OpTorch optimizes deep learning for resource-limited environments.
Large multi-tenant production clusters often have to handle a variety of jobs and applications with a variety of complex resource usage characteristics. It is non-trivial and non-optimal to manually create placement rules for scheduling that would decide which applications should co-locate. In this paper, we present De…
Paper presents efficient algorithms for convolutional neural networks using Winograd minimal filtering.
Designing deep learning models for highly-constrained hardware would allow imbuing many edge devices with intelligence. Microcontrollers (MCUs) are an attractive platform for building smart devices due to their low cost, wide availability, and modest power usage. However, they lack the computational resources to run ne…
Improves VQAs by balancing classical and quantum training resources.
FrostNet improves INT8 quantization efficiency in mobile networks.
Deep neural networks (DNNs) have been expanded into medical fields and triggered the revolution of some medical applications by extracting complex features and achieving high accuracy and performance, etc. On the contrast, the large-scale network brings high requirements of both memory storage and computation resource,…
New method improves neural architecture search by optimizing for both performance and diversity.
In recent years, Convolutional Neural Network (CNN) based methods have achieved great success in a large number of applications and have been among the most powerful and widely used techniques in computer vision. However, CNN-based methods are computational-intensive and resource-consuming, and thus are hard to be inte…
ALF reduces network parameters and operations by 70% and 61%, respectively, on embedded hardware.
Sequence-to-sequence models predict resource usage for co-scheduled jobs in data centers.
A generalized gamification framework is introduced as a form of smart infrastructure with potential to improve sustainability and energy efficiency by leveraging humans-in-the-loop strategy. The proposed framework enables a Human-Centric Cyber-Physical System using an interface to allow building managers to interact wi…
StatQAT optimizes quantization for deep networks, reducing computational cost and memory usage.
New framework guides resource usage to achieve sublinear regret in adversarial settings.
In this paper, we propose a gamification approach as a novel framework for smart building infrastructure with the goal of motivating human occupants to reconsider personal energy usage and to have positive effects on their environment. Human interaction in the context of cyber-physical systems is a core component and c…
Recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the u…
Bayesian Neural Networks (BNNs) have been proposed to address the problem of model uncertainty in training and inference. By introducing weights associated with conditioned probability distributions, BNNs are capable of resolving the overfitting issue commonly seen in conventional neural networks and allow for small-da…
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 …
This paper discusses e-commerce integration with SAP for Turkish businesses.
Recent machine learning methods use increasingly large deep neural networks to achieve state of the art results in various tasks. The gains in performance come at the cost of a substantial increase in computation and storage requirements. This makes real-time implementations on limited resources hardware a challenging …
Generative profiling improves real-time task timing for varied resource contexts.
Resource-efficient oblique trees reduce neural signal classification costs.
Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile devices requiring real-time processes with limited hardware resources. To address the…
We consider a fundamental dynamic allocation problem motivated by the problem of in financial markets, the mechanism underlying the short selling of stocks. A lender would like to distribute a finite number of identical copies of some scarce resource to clients, each of whom has a priv…
Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, onli…
Detecting inaccurate smart meters and targeting them for replacement can save significant resources. For this purpose, a novel deep-learning method was developed based on long short-term memory (LSTM) and a modified convolutional neural network (CNN) to predict electricity usage trajectories based on historical data. F…
EEG-TCNet improves MI-BMIs with high accuracy and low resource usage.
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…
Framework identifies comorbidities for frequent ED and inpatient visits.
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…
Developing active inference agents for edge devices with limited resources.
CLEANN detects and mitigates neural network Trojans without labeled data.
Quantum advantage in derivative pricing requires 8k qubits and 54M T-depth.
RiskNet predicts penalties in unreliable communication networks using GNNs.
The paper identifies when larger models improve predictions and proposes a switcher model.
SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.
RSmote improves PINNs accuracy with less memory usage.
Review of efficient neural networks for TinyML on resource-constrained devices.
Spectrum selectively trains LLMs based on SNR to save resources.
Training machine learning (ML) models on large datasets requires considerable computing power. To speed up training, it is typical to distribute training across several machines, often with specialized hardware like GPUs or TPUs. Managing a distributed training job is complex and requires dealing with resource contenti…
The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size. However, the efficacy of pruning based approaches has since been called into question. In this paper, we turn to distillation for model compression---specifically,…