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.
The paper optimizes neural network inference on mobile GPUs.
Researchers save memory on MCUs by reordering neural network operators.
Improved multi-user VoiceFilter-Lite model for speech recognition.
With the rapid emergence of a spectrum of high-end mobile devices, many applications that required desktop-level computation capability formerly can now run on these devices without any problem. However, without a careful optimization, executing Deep Neural Networks (a key building block of the real-time video stream p…
LITE efficiently estimates Gaussian PoM with linear time and memory complexity.
LITE models improve query-document relevance with learnable late interactions.
New method improves grouped convolutions on edge devices.
A simplified model for brain activity measurement.
CoCoPIE shows AI can run on regular devices without special hardware.
VoiceFilter-Lite separates speech from background in real-time for on-device speech recognition.
Two new Hie-TAN and Hie-TAN-Lite algorithms improve TAN for hierarchical feature spaces.
A framework for privacy-preserving DNN pruning and acceleration.
TensorFlow Probability introduces JointDistributions for probabilistic programming.
We propose a sample efficient stochastic variance-reduced cubic regularization (Lite-SVRC) algorithm for finding the local minimum efficiently in nonconvex optimization. The proposed algorithm achieves a lower sample complexity of Hessian matrix computation than existing cubic regularization based methods. At the heart…
Google's Machine Learning framework TensorFlow was open-sourced in November 2015 [1] and has since built a growing community around it. TensorFlow is supposed to be flexible for research purposes while also allowing its models to be deployed productively. This work is aimed towards people with experience in Machine Lea…
Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.
This paper improves financial simulations using Tensor Processing Units and Tensorflow.
TF-GNN simplifies graph neural networks in TensorFlow.
TensorFI injects faults in TensorFlow programs to assess their reliability.
TF-Coder simplifies tensor manipulation programming in TensorFlow.
New algorithm SELECT minimizes satisficing regret in bandits.
Trieste optimizes black-box functions using TensorFlow for efficient decision-making.
Batch-splitting (data-parallelism) is the dominant distributed Deep Neural Network (DNN) training strategy, due to its universal applicability and its amenability to Single-Program-Multiple-Data (SPMD) programming. However, batch-splitting suffers from problems including the inability to train very large models (due to…
PCONV combines fine-grained and coarse-grained pruning for efficient DNN inference on mobile devices.
The TensorFlow Distributions library implements a vision of probability theory adapted to the modern deep-learning paradigm of end-to-end differentiable computation. Building on two basic abstractions, it offers flexible building blocks for probabilistic computation. Distributions provide fast, numerically stable metho…
TensorFlow Probability MCMC toolkit improves MCMC efficiency for modern hardware.
Improves memory efficiency for meta-learning with large images.
Privacy is a major issue in learning from distributed data. Recently the cryptographic literature has provided several tools for this task. However, these tools either reduce the quality/accuracy of the learning algorithm---e.g., by adding noise---or they incur a high performance penalty and/or involve trusting externa…
This paper improves NAQ method for faster convergence on Tensorflow.
Spektral simplifies graph neural networks with TensorFlow and Keras.
AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns the structure of a neural network as an ensemble of subnetworks. We designed it…
Deep learning improves sensor performance optimization.
Recent work has shown that Field-Programmable Gate Arrays (FPGAs) play an important role in the acceleration of Machine Learning applications. Initial specification of machine learning applications are often done using a high-level Python-oriented framework such as Tensorflow, followed by a manual translation to either…
There is a perceived trade-off between machine learning code that is easy to write, and machine learning code that is scalable or fast to execute. In machine learning, imperative style libraries like Autograd and PyTorch are easy to write, but suffer from high interpretive overhead and are not easily deployable in prod…
GPflow is a Gaussian process library that uses TensorFlow for its core computations and Python for its front end. The distinguishing features of GPflow are that it uses variational inference as the primary approximation method, provides concise code through the use of automatic differentiation, has been engineered with…
TFCheck detects training issues in ML programs using TensorFlow.
TF Boosted Trees (TFBT) is a new open-sourced frame-work for the distributed training of gradient boosted trees. It is based on TensorFlow, and its distinguishing features include a novel architecture, automatic loss differentiation, layer-by-layer boosting that results in smaller ensembles and faster prediction, princ…
While accelerators such as GPUs have limited memory, deep neural networks are becoming larger and will not fit with the memory limitation of accelerators for training. We propose an approach to tackle this problem by rewriting the computational graph of a neural network, in which swap-out and swap-in operations are ins…
EagerPy simplifies writing code for multiple deep learning frameworks.
Non-determinism from GPUs dominates ResNet training accuracy variability.
Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling out DL training to a GPU-cluster. However, current distributed DL implementations can scale poorly due to substantial parameter synchronization over the network, because the high throughput of GPUs allows more data batc…
This paper compares machine learning models for pricing European options.
We describe TF-Replicator, a framework for distributed machine learning designed for DeepMind researchers and implemented as an abstraction over TensorFlow. TF-Replicator simplifies writing data-parallel and model-parallel research code. The same models can be effortlessly deployed to different cluster architectures (i…
With the advent of GPU-assisted hardware and maturing high-efficiency software platforms such as TensorFlow and PyTorch, Bayesian posterior sampling for neural networks becomes plausible. In this article we discuss Bayesian parametrization in machine learning based on Markov Chain Monte Carlo methods, specifically disc…
tf_geometric simplifies graph deep learning in TensorFlow.
InferPy simplifies probabilistic modeling with deep neural networks in Python.
Training modern deep learning models requires large amounts of computation, often provided by GPUs. Scaling computation from one GPU to many can enable much faster training and research progress but entails two complications. First, the training library must support inter-GPU communication. Depending on the particular …
A novel Python framework for Bayesian optimization known as GPflowOpt is introduced. The package is based on the popular GPflow library for Gaussian processes, leveraging the benefits of TensorFlow including automatic differentiation, parallelization and GPU computations for Bayesian optimization. Design goals focus on…