A basic question in the theory of fault-tolerant quantum computation is to understand the fundamental resource costs for performing a universal logical set of gates on encoded qubits to arbitrary accuracy. Here we consider qubits encoded with constant space overhead (i.e. finite encoding rate) in the limit of arbitrari…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Computation Overhead”
SRG improves optimization efficiency with reduced memory and computation overhead.
problem Limited applicability of variance-reduced optimization algorithms.
method SRG (stochastic reweighted gradient) using importance sampling.
result SRG outperforms SGD and provably improves convergence in strongly-convex cases.
ISAAC Newton uses input-based curvature for efficient training.
problem Efficient training in small-batch stochastic regimes.
method ISAAC Newton conditions gradients using selected second-order information based on input.
result Effective training even in small-batch stochastic regimes, competitive to first-order and second-order methods.
SOTERIA optimizes neural networks for secure inference with minimal overhead.
problem Protecting user privacy in ML-as-a-service models with low overhead.
method Neural architecture search with dual objectives of accuracy and cryptographic efficiency.
result SOTERIA constructs efficient models for secure inference.
CBC makes CNNs robust against adversarial attacks with minimal computational overhead.
problem Making CNNs robust against adversarial attacks without increasing computational complexity.
method CBC uses a stacked encoder-convolutional model where an auto-encoder encodes the input image, and the latent representation is used for classification.
result CBC is more robust to adversarial examples and has significantly lower computational complexity.
Information-theoretic Bayesian optimisation techniques have demonstrated state-of-the-art performance in tackling important global optimisation problems. However, current information-theoretic approaches require many approximations in implementation, introduce often-prohibitive computational overhead and limit the choi…
We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much one can trust predictions on new data. Recently promising works were pr…
HyperINF improves influence function estimation for large models with better accuracy and efficiency.
problem Inaccurate and computationally expensive influence function estimation for large-scale models.
method HyperINF leverages Schulz's iterative algorithm and GFIM for low-rank approximation of Hessian matrix.
result HyperINF achieves superior accuracy and performance compared to existing methods on LoRA-tuned models.
PruneFL reduces FL training time on edge devices by pruning model size.
problem Limited computation and communication resources on edge devices in FL.
method Adaptive and distributed parameter pruning during FL process.
result Pruned model converges to similar accuracy as original model with reduced training time.
METRO predicts reactions using minimal templates, reducing computational overhead and achieving state-of-the-art results.
problem Predicting possible reaction substrates for complex molecules from simpler precursors.
method METRO (Molecule-Edit Templates for RetrOsynthesis) uses minimal templates to predict reactions efficiently and accurately.
result METRO achieves state-of-the-art results on standard benchmarks, reducing computational overhead.
HCBM improves deep learning explainability by non-linear concept aggregation.
problem Lack of explainable and accurate predictions in deep learning for high-stake decisions.
method Introduce Hoeffding Concept Bottleneck Models (HCBM) using Hoeffding functional decomposition of gradient-boosted trees for non-linear and sparse concept aggregation.
result HCBM outperforms standard linear CBM and is robust to interconcept leakage.
The computation of convolution layers in deep neural networks typically rely on high performance routines that trade space for time by using additional memory (either for packing purposes or required as part of the algorithm) to improve performance. The problems with such an approach are two-fold. First, these routines…
This paper optimizes AI inference on edge devices with reduced communication and computation costs.
problem Efficiently performing AI inference on resource-constrained edge devices with reduced communication and computation costs.
method A three-step framework for effective inference: model split point selection, communication-aware model compression, and task-oriented encoding of intermediate features.
result Our proposed framework achieves a better trade-off and significantly reduces inference latency compared to baseline methods.
Top-k sparsification reduces deep learning communication costs.
problem Reducing communication overhead in distributed deep learning.
method Extensive experiments and theoretical analysis of Top-k sparsification.
result A tighter bound for Top-k operator derived, improving scaling efficiency.
A method predicts GNS of transformer layers using normalization layer norms.
problem Estimating gradient noise scale with minimal variance.
method Simultaneously compute per-example gradient norms and parameter gradients.
result Total GNS is predicted well by normalization layer GNS.
Nystrom approximation speeds up kernel model training.
problem Slow convergence in kernel models due to poor conditioning.
method Spectral preconditioning with Nystrom approximation for scalability.
result Nystrom approximation accelerates gradient descent nearly as well as exact preconditioner.
Generative Adapter adapts LMs with a single forward pass, reducing inference overhead.
problem Efficient adaptation of large language models for new contexts.
method Generative Adapter directly maps new contexts to low-rank LM adapters via self-supervised learning.
result Significant reduction in inference overhead with no need for fine-tuning.
Residual networks (ResNets) have recently achieved state-of-the-art on challenging computer vision tasks. We introduce Resnet in Resnet (RiR): a deep dual-stream architecture that generalizes ResNets and standard CNNs and is easily implemented with no computational overhead. RiR consistently improves performance over R…
In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreove…
Recently dictionary screening has been proposed as an effective way to improve the computational efficiency of solving the lasso problem, which is one of the most commonly used method for learning sparse representations. To address today's ever increasing large dataset, effective screening relies on a tight region boun…
FedLog reduces communication in federated learning by sharing data summaries.
problem Significant communication overhead in federated learning with large model parameters.
method Shares minimal sufficient statistics via Bayesian inference and differential privacy.
result High learning accuracy with low communication overhead.
Distributed model training suffers from communication overheads due to frequent gradient updates transmitted between compute nodes. To mitigate these overheads, several studies propose the use of sparsified stochastic gradients. We argue that these are facets of a general sparsification method that can operate on any p…
Paper proposes efficient BNN inference flow to reduce computation and memory costs.
problem High computation complexity in Bayesian Neural Networks (BNNs) limits deployment in power-constrained systems.
method Feature decomposition and memorization strategy to reduce computations and a memory-friendly computing framework to reduce memory overhead.
result Reduces computation by about half and energy consumption by 73% with 14% area overhead.
Paper proposes a method to estimate variance reduction in DNN training using importance sampling.
problem Challenges in assessing variance reduction during DNN training using importance sampling.
method Proposes a method for estimating variance reduction using minibatches sampled under importance sampling.
result Demonstrates consistent reduction in variance, improved training efficiency, and enhanced model accuracy.
SNNs optimize cross-market portfolios with neuromorphic computing, reducing computational overhead and improving returns.
problem Complex cross-market portfolio optimization with high-frequency, multi-dimensional datasets.
method Leaky Integrate-and-Fire neuron dynamics, adaptive thresholding, spike-timing-dependent plasticity, lateral inhibition, hierarchical clustering, population-based spike encoding, multiple decoding strategies.
result SNNs deliver superior risk-adjusted returns and reduced volatility compared to ANN benchmarks, with improved computational efficiency.
QPyTorch simplifies low-precision training simulations.
problem Empirical evaluation of low-precision training algorithms.
method Native PyTorch framework with efficient fused-kernel approach.
result Supports various low-precision configurations and rounding options.
Meta-Neighborhoodscs.LG
Meta-Neighborhoods adapts predictions based on input neighborhoods.
problem Adaptive prediction based on input neighborhoods for AI.
method Semi-parametric method with induced neighborhoods and meta-learning.
result Meta-Neighborhoods more accurately represents predictive distributions.
Sheaf Neural Networks improve graph learning with geometric insights.
problem Graph heterophily and over-smoothing issues.
method Inspired by Riemannian geometry, computes sheaves using orthogonal maps.
result Achieves promising results with reduced computational overhead.
MUMBO optimizes multiple tasks efficiently, even with low-cost related functions.
problem Efficiently optimizing multiple related functions with low-cost evaluations.
method Derives a novel multi-task version of entropy search.
result Robust performance with low computational overhead across various optimization challenges.
FOP improves deep learning optimizers with minimal computational overhead.
problem Training deep learning models can be hindered by high correlations and different scaling in parameter space.
method FOP uses first-order information to learn a preconditioning matrix that improves convergence without the high computational cost of second-order methods.
result FOP improves performance of standard deep learning optimizers on visual classification and reinforcement learning tasks.
GACTGAN synthesizes tabular data better with less computational overhead.
problem Synthesizing mixed tabular data while balancing risk and utility.
method Integrates Bayesian posterior approximation with Stochastic Weight Averaging-Gaussian (SWAG) in CTGAN.
result GACTGAN produces better synthetic data with reduced privacy risk.
Extended Kalman Filtering (EKF) can be used to propagate and quantify input uncertainty through a Deep Neural Network (DNN) assuming mild hypotheses on the input distribution. This methodology yields results comparable to existing methods of uncertainty propagation for DNNs while lowering the computational overhead con…
Deep learning reduces training overhead in massive MIMO systems.
problem Reducing training overhead in massive MIMO systems.
method Use of deep learning (NNs) to improve CSI acquisition and feedback processes.
result Significant improvements in performance and reduced complexity.
SPARC improves continual learning with minimal memory and computational overhead.
problem Efficient continual learning for deep neural networks.
method Combines task-specific working memories and task-agnostic semantic memory.
result Significantly reduces parameter usage (6% of full-model surrogates) while maintaining performance.
We consider the problem of learning a binary classifier from different data sources, among which at most an fraction are adversarial. The overhead is defined as the ratio between the sample complexity of learning in this setting and that of learning the same hypothesis class on a single data distribution. We pr…
The performance and efficiency of distributed machine learning (ML) depends significantly on how long it takes for nodes to exchange state changes. Overly-aggressive attempts to reduce communication often sacrifice final model accuracy and necessitate additional ML techniques to compensate for this loss, limiting their…
We study the collaborative PAC learning problem recently proposed in Blum et al.~\cite{BHPQ17}, in which we have players and they want to learn a target function collaboratively, such that the learned function approximates the target function well on all players' distributions simultaneously. The quality of the col…
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 …
New method reduces communication in deep learning training.
problem Communication overhead in distributed deep learning training.
method Random-block sparsification to reduce gradients communicated.
result Performance close to standard SGD with reduced communication.
Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion Modelscs.LG
VT-DIS improves sampling from Boltzmann distributions with minimal overhead.
problem Bias in Monte Carlo estimates from score-based diffusion models.
method Variance-Tuned Diffusion Importance Sampling (VT-DIS) adapts noise covariance to correct bias.
result VT-DIS achieves effective sample sizes of 80%, 35%, and 3.5% on benchmarks, using less computational budget.
Quantum systems with scrambling improve temporal information processing, but scaling requires exponential overhead.
problem Scalability and memory retention of quantum reservoirs in temporal information processing.
method Examined a quantum reservoir processing framework with scrambling reservoirs modeled by high-order unitary designs, analyzed in noiseless and noisy settings.
result Memory retention improves exponentially with reservoir size but worsens with reservoir iterations, requiring exponential shot overhead for scaling.
TCR improves DNN robustness to noisy labels with minimal overhead.
problem Training on noisy labeled datasets degrades DNN generalization.
method TCR combines original labels and previous epoch predictions for regularization.
result TCR consistently enhances DNN robustness to label noise.
TFiLM expands convolutional models' receptive field with minimal overhead.
problem Capturing long-range dependencies in sequential data.
method A novel architectural component using a recurrent neural network to modulate convolutional model activations.
result TFiLM significantly improves learning speed and accuracy on various tasks.
DCCNNs reduce computational overhead and ambiguity in convolutional neural networks.
problem Reducing computational overhead and ambiguity in convolutional neural networks.
method Introducing a primal learning problem and constructing a dual convex training program, using Fenchel conjugates and Karush-Kuhn-Tucker conditions.
result Eliminates ambiguity and reduces computational overhead in constructing a large kernel matrix.
Accelerates Bayesian optimization of function networks with partial evaluations.
problem Optimizing expensive-to-evaluate function networks with varying node costs.
method Proposes an accelerated algorithm that uses global Monte Carlo simulations to select node-specific candidate inputs.
result Achieves up to a 16x speedup over the original p-KGFN algorithm while maintaining competitive query efficiency.
A new method for efficient online federated learning reduces communication overhead.
problem Real-world limitations in online federated learning, such as heterogeneous client participation and communication delays.
method Proposes a communication-efficient asynchronous online federated learning (PAO-Fed) strategy.
result Achieves the same convergence properties as online federated stochastic gradient while reducing communication overhead by 98 percent.
Optical Echo State Network Reservoir Computingphysics.optics
Optical ESNs enable flexible, efficient machine learning with reduced energy.
problem Implementing universal computational capabilities in machine learning.
method Optical implementation of ESNs leveraging stimulated Brillouin scattering.
result Efficient, scalable, and memory-capable optical reservoir computing.
Improved few-shot learning with LSSVM and transductive modules.
problem Few-shot learning with limited data and samples.
method Introducing LSSVM as a base learner and transductive modules to enhance classification accuracy.
result FSLSTM achieves state-of-the-art performance on miniImageNet and CIFAR-FS benchmarks.