DLOPT simplifies deep learning hyper-parameter optimization.
problem Finding optimal network configurations in deep learning.
method Introduces a novel library for hyper-parameter optimization.
result Demonstrates effectiveness through use examples.
On-device research index
arXiv research
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Deep Learning Optimization Library”
LibAUC optimizes X-risks for AI tasks like CID, LTR, and CLR.
problem Optimizing risk functions in AI for tasks like classification, ranking, and representation learning.
method Developed a new mini-batch pipeline for deep X-risk optimization (DXO) algorithms.
result Achieved great success in solving CID, LTR, and CLR tasks with faster convergence and scalable performance.
MIOpen optimizes deep learning operators for GPUs, accelerating research.
problem Optimizing deep learning operators for efficient GPU execution.
method Highly optimized implementations, fusion, auto-tuning, bfloat16 support.
result Accelerates time to discovery in deep learning research.
McTorch simplifies manifold constraints in deep learning.
problem Constrained optimization in deep learning models.
method Extends PyTorch with manifold optimization capabilities.
result Facilitates easier implementation of manifold constraints.
fastai simplifies deep learning with a layered API.
problem Creating state-of-the-art deep learning models efficiently.
method Carefully layered architecture, Python type dispatch, GPU optimization, and novel callbacks.
result fastai achieves high performance with minimal compromise in usability and flexibility.
AITuning uses reinforcement learning to optimize communication libraries.
problem Optimizing communication libraries for better performance in parallel applications.
method Deep reinforcement learning applied to tuning communication libraries.
result Demonstrates the effectiveness of reinforcement learning for tuning communication libraries.
Formalizes and generalizes meta-learning patterns in deep and reinforcement learning.
problem Nested optimization problems in deep and reinforcement learning.
method Formalizes and proves requirements for a shared meta-learning pattern (GIMLI), derives a general-purpose algorithm, and provides a library.
result Demonstrates practical applications and ablation studies of the meta-learning framework and library.
Torch-Struct simplifies structured prediction for deep learning.
problem Difficulty in integrating structured prediction algorithms with deep learning frameworks.
method Develops a library (Torch-Struct) that integrates structured prediction with vectorized, auto-differentiation-based frameworks.
result Significant performance gains over fast baselines and cross-algorithm efficiency.
FCL3 learns from multiple representative models to adapt to new tasks.
problem Degradation of performance in lifelong learning models for new task environments.
method Two knowledge libraries: feature learning and model knowledge. Self-selection of representative models for new tasks.
result FCL3 achieves better performance than most lifelong learning frameworks.
We introduce a learning-based framework to optimize tensor programs for deep learning workloads. Efficient implementations of tensor operators, such as matrix multiplication and high dimensional convolution, are key enablers of effective deep learning systems. However, existing systems rely on manually optimized librar…
OpTorch optimizes deep learning for resource-limited environments.
problem Resource constraints in deep learning training.
method Optimized deep learning pipelines in training time and memory.
result Achieved similar accuracy to existing libraries with reduced memory usage.
Deep learning has enabled major advances in the fields of computer vision, natural language processing, and multimedia among many others. Developing a deep learning system is arduous and complex, as it involves constructing neural network architectures, managing training/trained models, tuning optimization process, pre…
GPflux simplifies deep Gaussian processes for Python.
problem Challenges in implementing deep Gaussian processes.
method Python library for Bayesian deep learning with DGPs.
result Efficient, modular, and extensible library for DGPs.
ChainerRL is a deep reinforcement learning library for Python.
problem Training and reproducing deep reinforcement learning algorithms.
method Built on Chainer framework, implements various DRL algorithms.
result Fosters reproducible research and replicates benchmark results.
BayesDLL offers a PyTorch library for Bayesian deep learning with large models.
problem Bayesian inference for large-scale deep networks.
method Variational inference, MC-dropout, stochastic-gradient MCMC, Laplace approximation.
result BayesDLL can handle Vision Transformers and pre-trained model weights as priors.
Bayesian learning made scalable with posteriors library.
problem Computational challenges in Bayesian learning with modern models.
method Introducing posteriors library and tempered MCMC.
result Bayesian approximations are useful and scalable.
CogDL simplifies graph deep learning experiments and benchmarks.
problem Challenges in training and evaluating graph neural networks.
method Unified design for training and evaluation, mixed precision training, efficient sparse operators, ease of use.
result CogDL is the most competitive graph library for efficiency and ease of use.
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural netw…
torchbearer simplifies deep learning model fitting in PyTorch.
problem Simplifying model fitting for researchers in deep learning.
method High-level metric and callback API for model persistence, learning rate decay, logging, and data visualization.
result Extensive documentation and built-in callbacks for various applications.
DGL simplifies graph neural network computations for faster, more efficient tensor operations.
problem Lack of efficient tools for graph neural network computations.
method Design principles and implementation of DGL, a graph-centric library for GNNs, using sparse tensor operations and parallelization.
result DGL significantly outperforms other GNN frameworks in speed and memory consumption.
A new kernel simplifies deep learning code and boosts performance.
problem Complex and hard-to-maintain DL codebases.
method Introducing a batch-reduce GEMM kernel for deep learning.
result Deep learning algorithms can be implemented with just 3K lines of code.
Orthogonium offers unified, efficient layers for robust deep learning.
problem Fragmented and computationally demanding implementations of orthogonal and 1-Lipschitz layers.
method Unified, efficient PyTorch library providing orthogonal and 1-Lipschitz layers.
result Reduced overhead and standardized tools for robust experimentation.
DeepRobust is a PyTorch library for adversarial attacks and defenses.
problem Addressing adversarial attacks and defenses in deep learning.
method Contains over 20 attack and defense algorithms for various deep learning architectures.
result Fosters research in adversarial learning with comprehensive and easy-to-use platform.
tf_geometric simplifies graph deep learning in TensorFlow.
problem Efficient graph deep learning in TensorFlow.
method Kernel libraries and infrastructures for GNNs.
result tf_geometric supports various graph tasks and provides efficient GNN models.
Deep learning uses complex networks for high-dimensional data.
problem Computational inefficiency in training deep learning models.
method Use of hierarchical latent variables, efficient linear algebra, SGD optimization, and batch sampling.
result Efficient training and inference possible with optimized algorithms.
Deep Learning Library (DLL) is a new library for machine learning with deep neural networks that focuses on speed. It supports feed-forward neural networks such as fully-connected Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). It also has very comprehensive support for Restricted Boltzmann …
This paper automates the creation of low precision deep learning operators for mobile devices.
problem Deploying large deep learning models on low power devices is challenging due to limited compute capabilities and energy budgets.
method Introduces a workflow to generate high-performance low precision deep learning operators for multiple CPU architectures, including optimizations like memory tiling and vectorization.
result 1-bit and 2-bit convolutions achieve up to 16x and 2.3x speedups over 16-bit integer baselines on ARM Cortex-A53 CPU.
Fortuna simplifies uncertainty quantification in deep learning.
problem Improving uncertainty estimates in deep learning models.
method Supports various calibration techniques including conformal prediction and scalable Bayesian inference.
result Simplifies benchmarking and builds robust AI systems.
This paper applies DRL to mean reversion trading problems.
problem Adopting DRL for financial trading problems.
method Integrates function properties into DRL for mean reversion trading.
result Demonstrates a highly-performant DRL solution for financial decision-making.
EagerPy simplifies writing code for multiple deep learning frameworks.
problem Code duplication and framework lock-in when using different deep learning libraries.
method Integrates multiple frameworks into a single Python framework.
result Automatic compatibility across PyTorch, TensorFlow, JAX, and NumPy.
SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networkscs.LG
SPFlow simplifies SPN-based probabilistic learning with a Python library.
problem Creating and manipulating deep probabilistic models efficiently.
method Provides a Python library with DSL for SPN creation, efficient inference routines, and structure learning.
result SPFlow enables quick and efficient probabilistic inference and learning for SPNs.
We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep and reinforcement learning approaches, ReLeaSE integrates two deep neural networks - generative and predictive - that are trained separately b…
ξ-torch simplifies physics-informed learning by providing differentiable functionals.
problem Training physics-informed deep neural networks requires differentiable physical simulations.
method ξ-torch offers a library of differentiable functionals for scientific simulations.
result Improves numerical stability and reduces memory requirements for higher order derivatives.
PyTorch combines usability and speed in deep learning.
problem Combining usability and speed in deep learning frameworks.
method Imperative programming style, Pythonic interface, hardware acceleration support.
result PyTorch achieves both usability and high performance.
Picasso is a new library for sparse learning problems in R and Python.
problem Sparse learning problems in high-dimensional data analysis.
method Unified framework of pathwise coordinate optimization with efficient active set selection strategies.
result picasso can efficiently handle large-scale problems.
DeepPurpose simplifies DL for DTI prediction.
problem Accurate prediction of drug-target interactions.
method Comprehensive deep learning library with 15 compound and protein encoders and 50 neural architectures.
result State-of-the-art performance on benchmark datasets.
Neural networks that compute over graph structures are a natural fit for problems in a variety of domains, including natural language (parse trees) and cheminformatics (molecular graphs). However, since the computation graph has a different shape and size for every input, such networks do not directly support batched t…
A deep probabilistic model analyzes DNA-encoded library data for efficient screening.
problem Complex data from DNA-encoded library experiments mask underlying signals.
method Compositional deep probabilistic model of DEL data, modeling latent reactions between synthons.
result DEL-Compose model demonstrates strong performance and valuable insights.
PyTorch Geometric accelerates deep learning on graphs.
problem Efficient deep learning on graph data.
method Library for graph data, including methods and efficient mini-batch handling.
result High data throughput achieved through sparse GPU acceleration.
Deeptime simplifies learning dynamical models from time series data.
problem Understanding complex systems through dynamical models from time series data.
method Various tools for estimating dynamical models including conventional and kernel/deep learning methods.
result Estimates dynamical models from time series data efficiently and with rich analysis methods.
BOML unifies meta-learning methods into a common bilevel optimization framework.
problem Meta-learning methods with diverse modeling aspects.
method Modularized bilevel optimization library in Python.
result Unified solution for various meta-learning formulations.
pyLOT library simplifies machine learning on 3D point clouds via linearized optimal transport.
problem Performing machine learning tasks on 3D point clouds.
method Linearized optimal transport (LOT) to embed distributions into Hilbert space, enabling linear machine learning.
result Downstream tasks on embedded representations are simplified to linear operations.
DeepOBS benchmarks deep learning optimizers.
problem Quantitative evaluation of deep learning optimizers.
method Python package with realistic benchmarks and back-ends.
result Automates benchmarking of stochastic optimizers.
JaxSGMC simplifies SG-MCMC for Bayesian deep learning.
problem Uncertainty quantification in deep learning models.
method Modular stochastic gradient MCMC in JAX.
result Facilitates trustworthy neural network predictions.
Deep learning can achieve outstanding results in various fields. However, it requires so significant computational power that graphics processing units (GPUs) and/or numerous computers are often required for the practical application. We have developed a new distributed calculation framework called "Sashimi" that allow…
This paper presents an open-source enforcement learning toolkit named CytonRL (https://github.com/arthurxlw/cytonRL). The toolkit implements four recent advanced deep Q-learning algorithms from scratch using C++ and NVIDIA's GPU-accelerated libraries. The code is simple and elegant, owing to an open-source general-purp…
Sherpa automates hyperparameter tuning for machine learning models.
problem Hyperparameter optimization for computationally expensive models.
method Powerful and interchangeable algorithms, interactive dashboard.
result Automates tedious aspects of model tuning.
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…