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.
This work tackles exploding inverses in INNs, revealing and mitigating their numerical non-invertibility.
New GPU kernels boost deep learning speed and memory efficiency.
PETRA enables parallel training of deep models with reversible architectures.
New method improves grouped convolutions on edge devices.
New algorithms find near-stationary points in convex optimization.
Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent requests, the latency during inference can also be very critical for costly comput…
Low precision operations can provide scalability, memory savings, portability, and energy efficiency. This paper proposes SWALP, an approach to low precision training that averages low-precision SGD iterates with a modified learning rate schedule. SWALP is easy to implement and can match the performance of full-precisi…
BatchNorm helps train quantized networks by avoiding gradient explosion.
Binarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Networks (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a widespread use. This work elaborates on this aspect introducing TentacleNet, a n…
Paper proposes a new binary quantization method for faster DNN inference.
Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is little knowledge of the resulting cost-benefit. We propose structural model distillation for memory reduction using a strategy that produces a …
The use of Gaussian process models is typically limited to datasets with a few tens of thousands of observations due to their complexity and memory footprint. The two most commonly used methods to overcome this limitation are 1) the variational sparse approximation which relies on inducing points and 2) the state-space…
We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support Vector Machine (SVM) in order to reduce the amount of computations, based on the pr…
Binary Neural Networks (BNNs) have been garnering interest thanks to their compute cost reduction and memory savings. However, BNNs suffer from performance degradation mainly due to the gradient mismatch caused by binarizing activations. Previous works tried to address the gradient mismatch problem by reducing the disc…
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference. The great success of DNNs motivates the pursuing of lightweight models for the deployment onto embedded devices. However, most of the prev…
Index structures are important for efficient data access, which have been widely used to improve the performance in many in-memory systems. Due to high in-memory overheads, traditional index structures become difficult to process the explosive growth of data, let alone providing low latency and high throughput performa…
SliceOut speeds up deep learning training without sacrificing accuracy.
Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production, especially when models need to be frequently re-trained on updated datasets. In…
Improved memory efficiency for deep neural networks.
Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of features, there are two issues to be further explored. First, the hard-assigned pse…
EiNets improve PCs for scalable probabilistic modeling.
LASER compresses recursive model activations by exploiting their low-dimensional structure.
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…
Paper finds sharpness differences in transformer blocks accelerating LLM training.
Safe screening rule reduces computational costs for Group OWL models.
TCGPN improves stock forecasting by capturing temporal correlation patterns.
GDML learns effective CG models from all-atom data.
New matrix approximation method using RBF components for better memory efficiency.
Deep neural network (DNN) quantization converting floating-point (FP) data in the network to integers (INT) is an effective way to shrink the model size for memory saving and simplify the operations for compute acceleration. Recently, researches on DNN quantization develop from inference to training, laying a foundatio…
Deep Convolutional Neural Networks (DCNNs) are currently popular in human activity recognition applications. However, in the face of modern artificial intelligence sensor-based games, many research achievements cannot be practically applied on portable devices. DCNNs are typically resource-intensive and too large to be…
Improves memory efficiency for meta-learning with large images.