Paper proposes MCMA architecture for neural approximate computing with higher invocation rate and energy savings.
problem Limited invocation rate of neural approximators leading to suboptimal energy efficiency.
method Introduces MCMA architecture with a multiclass classifier and multiple approximators, sharing hardware resources and efficiently swapping approximators.
result Significantly higher invocation rate and energy savings compared to existing methods.
Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approximation quality, existing works deploy two neural networks (NNs), e.g., an approximator and a predictor. The approximator provides the appro…
The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference. Conventional approximate computing focuses on balancing the efficiency-accuracy trade-off for existing pre-trained networks, which can lead to suboptimal solutions. In…
We provide a fast approximation to eNTKs for neural networks.
problem Efficiently computing eNTKs for large networks.
method Developed and proved the 'sum of logits' approximation.
result The 'sum of logits' approximation converges to eNTKs at initialization.
Paper proposes a log-domain training method to reduce neural network complexity.
problem High computational complexity in training deep neural networks limits real-time training.
method End-to-end training and inference scheme using approximate logarithmic operations in the log-domain.
result 16-bit log-based training achieves within 1% accuracy of floating-point baselines.
New methods improve statistical accuracy of complex models without high computational cost.
problem Improving statistical accuracy of complex models without high computational cost.
method Neural posterior and likelihood estimation (NPE and NLE) methods.
result NPE and NLE methods have similar theoretical guarantees to ABC and BSL, but achieve accuracy at a reduced computational cost.
We discuss approximation of functions using deep neural nets. Given a function f on a d-dimensional manifold Γ⊂Rm, we construct a sparsely-connected depth-4 neural network and bound its error in approximating f. The size of the network depends on dimension and curvature of the manifold Γ, the…
A new method for uncertainty estimation in neural networks using existing optimization steps.
problem Uncertainty quantification in deep neural networks.
method L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation.
result L2M method yields reasonable results without requiring changes in models or extra computational steps.
Modular method simplifies curvature computation in neural nets.
problem Efficient computation of curvature matrices for training neural nets.
method Modular backpropagation for block-diagonal approximations.
result Compact notation and easy integration into machine learning libraries.
New study shows exponential sample growth for ReQU neural networks.
problem Computing neural network approximations from samples is challenging.
method Information-based complexity tools.
result Functions can be approximated by ReQU neural networks at arbitrary rates but require exponentially growing samples.
NESTA accelerates neural networks by compressing Hamming weights.
problem Efficiently computing convolution layers in deep neural networks.
method NESTA reformats convolutions into 3imes3 batches and uses Hamming Weight Compressors to process each batch, approximating partial sums and adding residuals. result Significantly speeds up convolution computations with reduced energy consumption.
Neural methods improve likelihood-free inference with fewer simulations.
problem Inference when likelihood functions are unavailable.
method Comparing neural approaches for likelihood-free inference.
result Neural methods can achieve state-of-the-art results with fewer simulations.
Neural networks help create summary statistics for complex models.
problem Creating summary statistics for models with intractable likelihood functions.
method Infomax learning with neural networks to maximize mutual information.
result Improves performance of approximate Bayesian computation and neural likelihood methods.
Proposes TAGI for efficient Gaussian inference in Bayesian neural networks.
problem Efficient inference in Bayesian neural networks with complex architectures.
method Analytical method for tractable approximate Gaussian inference (TAGI).
result Matches performance of gradient-based methods with O(n) computational complexity. Neural networks approximate likelihood ratios for complex models.
problem Difficulty in computing likelihood ratios for modern models.
method Applying the likelihood ratio trick with neural network classifiers.
result Different neural network setups can approximate likelihood ratios with varying performance.
Neural networks improve Bermudan option pricing accuracy.
problem Pricing Bermudan options with conditional expectation challenges.
method Neural network approximations of conditional expectations.
result Longstaff and Schwartz algorithm convergence with neural networks.
Paper proves neural networks can be approximated using interval bounds.
problem Verifying safety and robustness of neural networks.
method Introduces interval universal approximation (IUA) theorem for neural networks.
result Neural networks can be approximated using interval bounds for any continuous function and squashable activation functions.
Bayesian methods enhance deep learning models by improving reliability and uncertainty.
problem Improving reliability and uncertainty awareness in deep learning models.
method Approximate Bayesian inference techniques, including SG-MCMC and VI, applied to deep learning models.
result Enhanced posterior inference for deep learning models, particularly in neural networks and generative models.
Study examines line search approximations for neural networks using MBSS.
problem Reducing computational cost in training large-scale neural networks.
method Empirical study of quadratic line search approximations for dynamic MBSS loss functions, enforcing different types of function and derivative information.
result Selectively enforcing information in approximations reduces the variance of predicted step sizes.
New method estimates uncertainty without sampling for neural networks.
problem Estimating epistemic uncertainty in neural networks for safety-critical applications.
method Approximated Variance Propagation without sampling.
result Significantly reduces computational overhead compared to sampling-based methods.
Large-scale deep neural networks are both memory intensive and computation-intensive, thereby posing stringent requirements on the computing platforms. Hardware accelerations of deep neural networks have been extensively investigated in both industry and academia. Specific forms of binary neural networks (BNNs) and sto…
New reservoir computing approach handles infinite-dimensional systems.
problem Approximating and generalizing complex input/output systems.
method Randomly generated echo state networks with neural networks.
result Proves universal approximation properties for new class of systems.
Greedy method adds neurons one by one for better function approximation.
problem Function approximation in neural networks.
method Growing deep neural network by adding one neuron at a time with non-linear activation.
result Accurate approximants for model problems in function approximation.
New method speeds up neural kernel computations for various activations.
problem Inefficient computation of neural kernels for general activations.
method Fast sketching method using truncated Hermite expansion.
result 106x speedup for approximate CNTK computation on CIFAR-10.
Optimal neural network approximation for Wasserstein gradient direction via convex optimization.
problem Approximating Wasserstein gradient direction with limited data.
method Two-layer networks with squared-ReLU activations, SDP relaxation.
result Optimal approximation of Wasserstein gradient direction in two-layer networks.
New algorithm for efficient prediction intervals in neural networks.
problem Challenges in estimating uncertainty in neural network predictions.
method Applies matrix sketching to approximate Jacobian matrix for efficient uncertainty estimation.
result Produces approximate prediction intervals with competitive performance.
Neural networks learn adaptive kernels that improve approximation and representation.
problem Improving neural network performance in approximating and representing functions from data.
method Dynamic reproducing kernel Hilbert space (RKHS) approach.
result Gradient flow in neural networks learns an adaptive RKHS representation and performs global least-squares projection.
Spiking neural networks enable efficient approximate Bayesian inference via permanent dropout.
problem Efficient uncertainty quantification in neural network predictions for critical tasks.
method Conversion of classical neural networks to spiking neural networks, applying permanent dropout for inference.
result Predictive distributions from spiking neural networks using permanent dropout are nearly identical to those from classical networks.
Approximate Bayesian Computation (ABC) methods are used to approximate posterior distributions in models with unknown or computationally intractable likelihoods. Both the accuracy and computational efficiency of ABC depend on the choice of summary statistic, but outside of special cases where the optimal summary statis…
Paper uses neural networks to efficiently compute vertex centrality measures in large networks.
problem Efficiently computing vertex centrality measures in massive real-world networks.
method Neural network learning algorithms to approximate centrality measures.
result Neural network regression model outperforms other techniques in terms of solution quality and computation time.
Two new criteria help understand the advantage of deep neural networks.
problem Understanding the advantage of deepening neural networks.
method Proposed two new criteria to evaluate the expressivity of functions computable by deep neural networks.
result Increasing layers is more effective than increasing units in improving the expressivity of deep neural networks.
Proposes DAK model for improved GP computations.
problem Challenges in high-dimensional GP layers in DKL.
method Additive structure and induced prior approximation for GP units.
result Outperforms state-of-the-art DKL methods in regression and classification.
RFAD uses random features to speed up dataset distillation.
problem Efficiently compress large datasets for reduced storage and computation.
method Random feature approximation of the Neural Network Gaussian Process kernel.
result At least 100-fold speedup over KIP with competitive accuracy.
Pseudo-Likelihood Inference improves ABC for high-dimensional Bayesian inference.
problem Intractable likelihood in Bayesian system identification.
method PLI combines neural approximation with integral probability metrics and adaptive bandwidth.
result PLI outperforms SNPE on challenging tasks, especially with more data.
Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. The involved deep neural network architectures and computational issues have been well studied in machine learning. But there lacks a theoretical foundation for understanding the approximation…
MPNN improves on UniFL approximation with provable guarantees.
problem Uniform Facility Location (UniFL) optimization problem.
method Graph Neural Network (MPNN) incorporating approximation-algorithmic principles.
result Empirically outperforms standard approximation algorithms.
PILNO uses neural operators to solve PDEs efficiently on point clouds.
problem Solving partial differential equations (PDEs) on point cloud data efficiently.
method Physics-informed low-rank neural operator framework combining low-rank kernel approximations and an encoder-decoder architecture.
result PILNO efficiently approximates solution operators of PDEs on point cloud data, satisfying PDE constraints and boundary conditions.
A framework explains neural network decisions using rate-distortion theory.
problem Interpreting neural network decisions as an optimisation problem.
method Rate-distortion framework, NP-hard problem, heuristic solution strategy.
result The problem is NP-hard and NP-complete, making it computationally challenging.
Quantum neural networks approximate periodic functions more efficiently.
problem Approximating periodic functions with quantum neural networks.
method Using Jackson's inequality to construct a QNN that approximates a trigonometric polynomial of the function.
result Quantum neural networks can achieve better approximation results with fewer parameters for smoother functions.
QLA improves Bayesian uncertainty estimation for DNNs without increasing computational cost.
problem Overconfident out-of-distribution predictions from DNNs.
method Proposes Quadratic Laplace Approximation (QLA) to improve Bayesian uncertainty quantification.
result QLA yields modest yet consistent uncertainty estimation improvements over Linearized Laplace Approximation (LLA) on five regression datasets.
The paper approximates financial derivatives using neural networks and iterated integrals.
problem Approximating p-integrable financial derivatives. method Using iterated Stratonovich integrals and neural networks.
result Approximate solutions to the Lp-hedging problem. Proposes SE(3) equivariant graph neural networks with local frames for efficient geometric approximation.
problem Equivariance in deep learning for arbitrary transformations, especially in physics.
method Introduces SE(3) equivariant graph neural networks with complete local frames to efficiently approximate geometric quantities.
result Achieves best or competitive performance in Newton mechanics modeling and equilibrium molecule conformation generation.
This study shows neural nets can approximate Turing machines with meaningful statistical properties.
problem Theoretical limitations in approximating Turing machines with neural networks.
method Formal definition of statistically meaningful approximation, analysis of boolean circuits and Turing machines using neural nets.
result Transformers can statistically meaningfully approximate Turing machines with polynomial sample complexity.
New LTC RNNs can approximate any continuous system with fewer units.
problem Approximating continuous dynamical systems with neural networks.
method Introducing LTC RNNs with variable time-constant synaptic transmission.
result LTC RNNs can approximate any n-dimensional continuous dynamical system. Survey examines deep neural networks' ability to approximate functions.
problem Approximation of target functions by deep neural networks.
method Examination of feed-forward and residual architectures, focusing on optimization problems in regression and classification.
result Deep neural networks can approximate functions effectively, especially with ReLU activation functions.
Bayesian Deep Learning tackles inverse problems with neural networks and approximate computations.
problem Solving inverse problems with indirect measurements and uncertainties.
method Bayesian Deep Learning, using neural networks and approximate computations.
result Effective solutions for inverse problems using Bayesian Deep Learning.
Simulation-based inference methods can produce unreliable posterior approximations.
problem Reliability of simulation-based inference methods for scientific use cases.
method Benchmarked algorithms including Neural Posterior Estimation, Neural Ratio Estimation, Sequential Neural Likelihood, and Approximate Bayesian Computation.
result Ensembling posterior surrogates provides more reliable approximations.
Efficient PI for neural networks without distributional assumptions.
problem No distributional assumptions for efficient predictive inference.
method Differential privacy and linear approximation for leave-one-out models.
result Rigorous coverage guarantees with reduced computation.