Many theories of deep learning have shown that a deep network can require dramatically fewer resources to represent a given function compared to a shallow network. But a question remains: can these efficient representations be learned using current deep learning techniques? In this work, we test whether standard deep l…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “efficient deep networks”
Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?" by introducing the notion of synthesizing new highly efficient, yet powerful deep neural networks over successive generations via an ev…
Deep networks can learn functions approximated by shallow networks, but not all functions.
problem The learnability of functions by deep neural networks and the approximation capacity of simpler classes.
method Study the connection between learnability and approximation capacity of functions by deep neural networks and simpler classes.
result A necessary condition for a function to be learnable by deep neural networks is to be approximable by shallow networks.
Proposes efficient training method for deep thin networks.
problem Deploying deep learning models with accuracy and compactness.
method Three-stage method: widen, warm up, fine tune.
result Deep thin networks trained with method outperform standard deep networks.
Deep networks can approximate score functions in high-dimensional graphical models efficiently.
problem Approximation efficiency of score functions by deep neural networks in high-dimensional graphical models like Markov random fields.
method Variational inference denoising algorithms and efficient neural network representation.
result Efficient sample complexity bound for diffusion-based generative modeling when score functions are learned by deep neural networks.
Evolution in Groups: A deeper look at synaptic cluster driven evolution of deep neural networkscs.NE
A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simula…
Proves deep networks can learn hierarchical structures efficiently.
problem Understanding how deep networks learn hierarchical structures in data.
method Random Hierarchy Models, gradient-based methods, layerwise training.
result Proves deep networks can efficiently learn hierarchical structures.
Deep learning improves portfolio optimization efficiency.
problem Efficient frontier calculation in high-dimensional finance problems.
method Deep neural networks for portfolio optimization with added constraints.
result A new projected feedforward network outperforms classical methods.
There has been significant recent interest towards achieving highly efficient deep neural network architectures. A promising paradigm for achieving this is the concept of evolutionary deep intelligence, which attempts to mimic biological evolution processes to synthesize highly-efficient deep neural networks over succe…
Deep RNNs compute American option prices and deltas efficiently.
problem Computing prices and deltas of high-dimensional American options.
method Two deep RNNs, one for price and one for delta, learn over spacetime.
result Linear time and constant memory cost compared to feedforward networks.
Securely trains neural networks remotely with deep learning's flaws.
problem Secure and efficient training of neural networks over unsecured channels.
method Leverages deep learning's weaknesses for secure training.
result Efficient and secure training of neural networks remotely.
Stacking improves deep neural network training efficiency.
problem Improving the efficiency of training deep neural networks.
method Proposes stacking as a form of accelerated gradient descent.
result Proves stacking provides accelerated training for certain deep linear residual networks.
Increasing input dimensionality improves deep RL performance and sample efficiency.
problem Real-world reinforcement learning applications often lack sufficient training data.
method Proposed an online feature extractor network (OFENet) to improve deep RL performance and sample efficiency.
result RL agents learn more efficiently with high-dimensional input representations than with lower-dimensional state observations.
Deep quantum neural networks applied to finance for efficient risk management.
problem Efficiently solving numerical problems in finance, especially risk management.
method Application of deep quantum neural networks to finance, focusing on implied volatilities, option prices, and Greeks.
result Deep quantum neural networks can compute Greeks analytically and efficiently solve financial numerical problems.
Deep neural networks are a powerful tool for feature learning and extraction given their ability to model high-level abstractions in highly complex data. One area worth exploring in feature learning and extraction using deep neural networks is efficient neural connectivity formation for faster feature learning and extr…
Proposes using gradients as features for efficient deep learning adaptation.
problem Efficient deep representation learning for different tasks.
method Designs a linear model incorporating gradients and activations of a pre-trained network.
result Shows strong results across various tasks and datasets.
We show that a collection of Gaussian mixture models (GMMs) in can be optimally classified using neurons in a neural network with two hidden layers (deep neural network), whereas in contrast, a neural network with a single hidden layer (shallow neural network) would require at least neurons …
We consider the ability of deep neural networks to represent data that lies near a low-dimensional manifold in a high-dimensional space. We show that deep networks can efficiently extract the intrinsic, low-dimensional coordinates of such data. We first show that the first two layers of a deep network can exactly embed…
Improved memory efficiency for deep neural networks.
problem Increasing model size makes deep learning less accessible.
method Inductive-bias-driven network design and manifold-oriented regularization.
result Improved performance and generalization error compared to traditional methods.
We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the D2NN itself. By pruning unnecessary computation depending on input, D2NNs provide a…
New method creates coresets for deep neural networks efficiently.
problem Efficiently handling large data streams with limited resources.
method Cardinality-constrained bilevel optimization for deep neural networks.
result Demonstrated efficient generation of coresets for deep neural networks.
New deep learning architecture learns martingales efficiently.
problem Efficiently learning martingales in financial derivatives pricing.
method High-order weak approximation algorithms of Runge-Kutta type.
result Deep neural networks based on this architecture learn martingales effectively.
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…
New insights into training deep networks with low rank layers.
problem Efficiency in training deep neural networks.
method Analysis of techniques for training in low rank space.
result Falsified common beliefs in training deep networks.
Examines learning efficiency in neural networks and related models.
problem Analyzing efficiency in deep learning models with singular learning coefficients.
method Examined learning coefficients in neural networks and three-layer neural networks with ReLU units.
result Extended results to include Softmax function, providing a broader understanding of learning efficiency.
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep neural network compression and speed-up methods are very effective for training compact deep models, …
New insights into neural network training efficiency.
problem Understanding the optimal initialization for deep neural networks.
method Exploring the edge of chaos and saturation of tanh activation function.
result The line of uniformity in phase space intersects the edge of chaos, indicating saturation begins to hinder training efficiency.
Improved sample efficiency with normalized RBF kernels in neural networks.
problem Learning more with less data in deep learning models.
method Two-phase method to train neural networks with normalized RBF kernels as output layer.
result Normalized RBF kernel networks achieve higher sample efficiency, compactness, and separability.
Enhances hedging strategies using deep neural networks.
problem Optimizing risks and returns in financial hedging.
method Integrates deep neural networks and random forest classifiers to find optimal hedging strategies.
result Improved hedging strategies with lower costs and risks.
Efficiently maximizes AUC with deep nets, reducing communication rounds.
problem Maximizing AUC with deep neural networks in a distributed setting.
method Communication-efficient distributed optimization algorithm for non-convex concave AUC maximization.
result Achieves linear speedup with significantly fewer communication rounds.
Rational neural networks approximate functions more efficiently with less depth.
problem Choosing optimal nonlinear activation functions in neural networks.
method Rational activation functions with optimal bounds and efficiency proofs.
result Rational neural networks approximate smooth functions more efficiently than ReLU networks with exponentially smaller depth.
New deep network derived from rate reduction principles, explaining features and efficiency.
problem Understanding and optimizing deep learning architectures.
method Gradient ascent scheme for rate reduction leading to multi-layer deep network.
result Explicitly constructed multi-layer network with precise optimization and interpretation.
New method grows deep networks efficiently by dynamically pruning and growing layers.
problem Training deep networks is computationally expensive and inefficient.
method Structured continuous sparsification starting from a small seed architecture.
result 49.7% inference FLOPs and 47.4% training FLOPs savings with 75.2% top-1 accuracy.
Paper develops efficient variational inference for sparse deep learning with theoretical guarantees.
problem Sparse deep learning's challenge of huge storage consumption and sparse structure recovery.
method Bayesian treatment with spike-and-slab priors and continuous relaxation of Bernoulli distribution for computationally efficient variational inferences.
result Provides variational posterior contraction rate, justifying consistency of the proposed method.
Develops a deep non-stationary kernel for non-stationary spatio-temporal point processes.
problem Capturing non-stationary dependencies in point process data.
method Approximates the influence kernel with a novel low-rank decomposition and introduces a log-barrier penalty to maintain non-negativity.
result Demonstrates superior performance and computational efficiency compared to state-of-the-art methods.
New method selects neural network architectures without needing data.
problem Choosing efficient deep neural network architectures.
method Developed the deep frame potential to quantify network capacity.
result Deep frame potential correlates with generalization error.
Proposes DGCN with trajectory sampling for data-efficient policy search in MBRL.
problem Improving data efficiency in model-based reinforcement learning.
method Combines trajectory sampling and DGCN for uncertainty propagation in probabilistic world models.
result Improves sample-efficiency over other uncertainty propagation methods and probabilistic models.
Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and inference in numerical formats optimized for deep learning. Despite advances in limited precision inference in recent years, training of neura…
WaveQ uses sinusoidal regularization to optimize deep quantization for neural networks, improving both efficiency and accuracy.
problem Deep quantization reduces bitwidth but can lead to significant accuracy loss due to inter-layer dependencies.
method WaveQ employs sinusoidal regularization to learn multiple quantization parameters during gradient-based training, balancing compute efficiency and accuracy.
result WaveQ achieves accuracy preservation and efficiency gains across various deep networks, outperforming state-of-the-art techniques.
Deep neural networks and the ENO procedure are both efficient frameworks for approximating rough functions. We prove that at any order, the ENO interpolation procedure can be cast as a deep ReLU neural network. This surprising fact enables the transfer of several desirable properties of the ENO procedure to deep neural…
Deep neural networks continue to show improved performance with increasing depth, an encouraging trend that implies an explosion in the possible permutations of network architectures and hyperparameters for which there is little intuitive guidance. To address this increasing complexity, we propose Evolutionary DEep Net…
FBSJNN solves PIDEs and FBSDEJs with deep learning, offering theoretical and numerical efficiency.
problem Solving Partial Integro-Differential Equations and Forward-Backward Stochastic Differential Equations with Jumps.
method FBSJNN framework using a single neural network for both solution approximation and non-local integral.
result FBSJNN achieves numerical solutions with a relative error of , demonstrating efficiency.
Proposes a sample-efficient method for uncertainty estimation in deep learning.
problem Inaccurate uncertainty estimation in deep learning models, especially with limited data.
method Probabilistic Neighbourhood Component Analysis (PCA) for sample-efficient uncertainty estimation.
result Demonstrates superior uncertainty quantification compared to state-of-the-art methods.
DQA efficiently quantizes deep neural network activations for resource-constrained devices.
problem Efficiently quantizing deep neural network activations for resource-constrained devices.
method DQA uses simple shifting-based operations and Huffman coding for sub-6-bit quantization.
result DQA achieves significantly better accuracy than direct quantization and state-of-the-art methods.
Deep learning upscales geologic models efficiently.
problem Upscaling large-scale geologic models for efficient simulation.
method Theory-guided convolutional neural network (TgCNN) trained to approximate hydraulic conductivity relationships.
result Deep learning method achieves equivalent upscaling accuracy to numerical methods but with significantly improved efficiency.
Efficient equivariant MobileNetV2 for medical applications on mobile devices.
problem Limited computational resources for deep learning models in medical applications.
method Design and optimize an equivariant version of MobileNetV2 with model quantization.
result Achieved close-to state-of-the-art performance on medical dataset with improved efficiency.
A hybrid neural network optimizes AI deployment on edge and cloud for energy efficiency.
problem Energy and resource constraints in edge devices for deep learning models.
method Conditionally deep hybrid neural network with quantized layers at edge and full-precision layers at cloud.
result Early classification at the edge reduces energy consumption by 5.5x on CIFAR-10 dataset.
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and…