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.
Efficient equivariant MobileNetV2 for medical applications on mobile devices.
Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuit…
Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by imposing sparsity inducing regularizers. In this paper, we investigate two techniques for group-wise pruning during training in order to improve …
New multigrid approach reduces CNN parameters by focusing on structured convolutions.
We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given search space by optimizing over a loss function which accounts for accuracy and …
DONNA rapidly finds optimal neural networks across diverse spaces.
As neural networks revolutionize many applications, significant privacy conflicts between model users and providers emerge. The cryptography community developed a variety of techniques for secure computation to address such privacy issues. As generic techniques for secure computation are typically prohibitively ineffec…
We present a logarithmic-scale efficient convolutional neural network architecture for edge devices, named WaveletNet. Our model is based on the well-known depthwise convolution, and on two new layers, which we introduce in this work: a wavelet convolution and a depthwise fast wavelet transform. By breaking the symmetr…
A new method speeds up spectral normalization for neural nets.
Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices. To address that issue, we envision sharing the computational costs of inference between local devices and the cloud, taking advantage of the compression performed by the f…
In this paper we propose the macroblock scaling (MBS) algorithm, which can be applied to various CNN architectures to reduce their model size. MBS adaptively reduces each CNN macroblock depending on its information redundancy measured by our proposed effective flops. Empirical studies conducted with ImageNet and CIFAR-…
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden. In this work, we propose a lightweight yet high-performing baseline network inspired by MobileNetV2, which replaces square convolutional kernels with unidirectional ones …
Greedy pruning reduces neural networks by a logarithmic number of tickets, improving accuracy.
We present a theoretical and experimental investigation of the quantization problem for artificial neural networks. We provide a mathematical definition of quantized neural networks and analyze their approximation capabilities, showing in particular that any Lipschitz-continuous map defined on a hypercube can be unifor…
DBQ quantizes lightweight networks efficiently for resource-constrained devices.
Convolutional Neural Network (CNN) based Deep Learning (DL) has achieved great progress in many real-life applications. Meanwhile, due to the complex model structures against strict latency and memory restriction, the implementation of CNN models on the resource-limited platforms is becoming more challenging. This work…
Quantizing large Neural Networks (NN) while maintaining the performance is highly desirable for resource-limited devices due to reduced memory and time complexity. It is usually formulated as a constrained optimization problem and optimized via a modified version of gradient descent. In this work, by interpreting the c…
Rapid growth in delivery and freight transportation is increasing in urban areas; as a result the use of delivery trucks and light commercial vehicles is evolving. Major cities can use traffic counting as a tool to monitor the presence of delivery vehicles in order to implement intelligent city planning measures. Class…
DJPQ optimizes neural network pruning and quantization for hardware efficiency.
Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaining a search cost orders of magnitude lower than reinforcement learning (RL) based NAS. However, DNAS…
Greedy selection finds smaller, more accurate subnetworks.
LTP learns per-layer thresholds for efficient pruning of deep networks.
Paper presents a method to disrupt deep uncertainty estimation without affecting accuracy.
In the semantic segmentation of street scenes the reliability of the prediction and therefore uncertainty measures are of highest interest. We present a method that generates for each input image a hierarchy of nested crops around the image center and presents these, all re-scaled to the same size, to a neural network …
i-SpaSP prunes neural networks by identifying important groups of parameters, improving pruning efficiency.
Deep Learning detects cyclists' orientation for safer roads.
This study automates blood cell classification using computer vision.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
Joslim optimizes both width and weight configurations for slimmable neural networks, improving model efficiency.
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.
Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet).…