Research
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

130260389519 · Jun 202019922001200920172026
48 results for inference cost reduction

U-statistics improve gradient estimation in importance-weighted variational inference.

problem High variance in gradient estimation for importance-weighted variational inference.
method Use U-statistics to average base gradient estimators on overlapping batches of size m, achieving lower variance.
result U-statistic variance reduction leads to modest to significant improvements in inference performance.

Bayesian framework reduces high-dimensional GP modeling costs.

problem Challenges in fitting Gaussian processes to high-dimensional inputs.
method Hierarchical Bayesian model with orthonormal projection matrix, incorporating Deep Gaussian Processes.
result Improves predictive performance and uncertainty quantification.

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.

Extends dimension reduction to data-driven settings without gradients.

problem Gradient-based dimension reduction limitations in data-driven settings.
method Score ratio matching framework, tailored parameterization, regularization, eigenvalue deflation.
result Outperforms standard score-matching for problems with low-dimensional structure.

MASnet enhances speech on mobile devices with low latency.

problem Efficiently enhancing speech on mobile devices with low latency.
method MASnet processes linear-scale spectrograms, using ratio masks to enhance noisy frames, and operates in low-latency incremental inference mode.
result MASnet achieves efficient speech enhancement with low latency, reducing FMA/s operations.

Gradual pruning reduces inference cost by pruning least important channels during training.

problem Reduction of deep neural network inference cost.
method Gradual channel pruning using feature relevance scores during training.
result Achieved significant model compression with minimal accuracy loss.

Sliced Inverse Regression reduces parameter space for estimating complex financial models.

problem High-dimensional parameter space in stochastic differential equations.
method Sliced Inverse Regression for dimension reduction.
result Reduced computational costs in estimating parameters.

Bayesian approach reduces FL communication cost by one-shot.

problem High communication cost in optimization-based FL for high-dimensional models.
method Bayesian pseudocoresets and function-space inference for one-shot FL.
result Achieves prediction performance competitive to state-of-the-art with up to 2 orders of magnitude reduction in communication cost.

This paper develops scalable control variates for Monte Carlo methods using stochastic optimization.

problem Reducing variance in Monte Carlo estimators for large-scale problems.
method Control variates based on Stein operators, optimized through stochastic optimization.
result Novel theoretical results and empirical validations show effective variance reduction.

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…

2018-10-01abs ↗pdf ↗

This paper introduces channel gating, a dynamic, fine-grained, and hardware-efficient pruning scheme to reduce the computation cost for convolutional neural networks (CNNs). Channel gating identifies regions in the features that contribute less to the classification result, and skips the computation on a subset of the …

2018-05-29abs ↗pdf ↗

TERA method speeds up derivative Gaussian processes in high dimensions.

problem High-dimensional function evaluations and gradient computations are computationally expensive.
method TERA uses exact gradient reduction to decouple nn and dd from the computational cost.
result TERA achieves state-of-the-art predictive accuracy with orders of magnitude faster computation.

A new method reduces inference cost for FwFM by allowing it to scale with item fields only.

problem High computational cost in FwFM for large field counts.
method Low-rank diagonal plus symmetric decomposition for field-wise interactions.
result Aggressive rank reduction outperforms pruning in accuracy and speed.

Two new estimators reduce costs and improve accuracy for EHR outcome prediction.

problem Sparse estimate distributions, high computational cost, and high sampling variance in EHR outcome prediction.
method Proposed SCOPE and REACH estimators that leverage next-token probability distributions.
result SCOPE and REACH match Monte Carlo accuracy with token reductions of 2.5-3.4 times and variance guarantees.

Paper proposes a method to use in silico experiments with foundation models to reduce sample size.

problem Costly and uncertain randomized experiments.
method Integrates predictions from multiple foundation models with experimental data.
result Estimator offers substantial precision gains, equivalent to a 20% reduction in sample size.

SSVI efficiently trains sparse Bayesian neural networks with minimal compression and performance loss.

problem Efficiently training Bayesian neural networks with uncertainty quantification.
method SSVI optimizes a sparse subspace basis selection and its parameters alternately, guided by weight distribution statistics.
result SSVI achieves significant compression (10-20x model size reduction) with minimal performance drop (under 3%) and FLOPs reduction (up to 20x) compared to dense Variational Inference.

A new approach reduces the size of prediction sets in CP, making it more efficient.

problem Large and costly prediction sets in standard CP.
method Expand correctness criterion to include inferred admissible answers, and use prediction cascades to prune implausible labels.
result Empirically effective in natural language processing and drug discovery.

Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuit…

2018-11-26abs ↗pdf ↗

We discuss investment allocation to multiple alpha streams traded on the same execution platform with internal crossing of trades and point out differences with allocating investment when alpha streams are traded on separate execution platforms with no crossing. First, in the latter case allocation weights are non-nega…

2014-05-19abs ↗pdf ↗

Wide adoption of complex RNN based models is hindered by their inference performance, cost and memory requirements. To address this issue, we develop AntMan, combining structured sparsity with low-rank decomposition synergistically, to reduce model computation, size and execution time of RNNs while attaining desired ac…

2019-10-02abs ↗pdf ↗

SmartDeal reduces energy and storage costs for deep neural networks.

problem Heavy parameterization of deep neural networks leads to inefficient use of DRAM.
method SmartDeal decomposes weights into a small basis matrix and a structurally sparse coefficient matrix, quantized to power-of-2.
result Up to 2.44x energy efficiency improvement in inference and 10.56x reduction in training energy.

ACE improves GBI for simulators by approximating cost functions, making inference more efficient.

problem Inference for misspecified simulators is overly restrictive.
method Amortized cost estimation (ACE) for Generalized Bayesian Inference (GBI).
result ACE provides accurate cost predictions and more efficient inference.

Paper improves tree probability estimation using stochastic optimization and variance reduction.

problem Improving tree probability estimation in phylogenetic inference.
method Introduces computationally efficient methods for training SBNs and variance reduction for optimization.
result Methods outperform previous baseline methods in tree topology probability estimation and Bayesian phylogenetic inference.

FAQ efficiently evaluates LLMs with statistical guarantees using adaptive query selection.

problem Efficiently evaluating many LLMs on a large suite of benchmarks is expensive.
method FAQ uses Bayesian factor models, adaptive sampling, and proactive active inference to select queries.
result FAQ delivers up to 5x effective sample size gains over baselines, matching CI width with fewer queries.

We consider active maximum a posteriori (MAP) inference problem for Hidden Markov Models (HMM), where, given an initial MAP estimate of the hidden sequence, we select to label certain states in the sequence to improve the estimation accuracy of the remaining states. We develop an analytical approach to this problem for…

2014-11-03abs ↗pdf ↗

Physics-informed model reduces RBC simulation costs.

problem Computational infeasibility of direct numerical simulations for turbulent systems.
method Combines CNN and recurrent architecture, penalized with PDEs, uses conformal prediction.
result Significant reduction in computational cost for long-term simulations.

Persistent sampling improves SMC efficiency by retaining and reusing particles.

problem High computational costs and particle impoverishment in SMC.
method Persistent sampling (PS) retains and reuses particles from all prior iterations, using multiple importance sampling and resampling from a mixture of historical distributions.
result PS achieves more accurate posterior approximations and lower variance in marginal likelihood estimates without additional likelihood evaluations.

DFR reduces the computational cost of sparse-group lasso and adaptive sparse-group lasso.

problem Sparse-group lasso's computational expense and need for tuning.
method Dual Feature Reduction (DFR) using strong screening rules and dual norms.
result DFR drastically reduces computational cost without affecting solution optimality.

New method reduces deep learning training costs by approximating vector-jacobian products.

problem Efficiently training deep neural networks with reduced computational and memory costs.
method Randomized, unbiased approximations of vector-jacobian products during backpropagation.
result Validated potential for reducing deep learning training costs through unbiased estimates.

Designs a neural network to reduce training cost by mapping to higher dimensions.

problem High training cost in neural networks.
method Maps feature vectors to higher dimensional space, designs weight matrices to reduce cost, uses convex constraints.
result Reduces training cost as the number of layers increases, without cross-validation.

Paper interprets UMAP and t-SNE as probabilistic MAP inference.

problem Understanding and interpreting UMAP and t-SNE.
method Interprets UMAP and t-SNE as MAP inference methods corresponding to a probabilistic model of the graph Laplacian.
result Shows UMAP and t-SNE can be understood as probabilistic inference methods.

Efficient Winograd convolution for INT8 networks using RNS.

problem Difficulty in applying Winograd algorithm to low-precision quantized networks.
method Extends Winograd algorithm to Residue Number System (RNS) for efficient INT8 convolution.
result Arithmetic complexity reduction up to 7.03x with performance improvement up to 2.30x-4.69x.