We accelerate the power method for strong low-rank approximation using fast sketching.
problem Efficiency bottleneck in power method for large target ranks.
method Developed an algorithmic and theoretical framework for accelerating the power method using fast sketching.
result Simple and provably efficient methods for singular value decomposition, low-rank factorization, and Nyström approximation.
Approximate multipliers boost CNN training speed, power, and area at slight accuracy cost.
problem Improving CNN training performance in terms of speed, power, and area.
method Simulation of approximate multipliers' impact on CNN training, hybrid training method combining approximate and exact multipliers.
result Using approximate multipliers for most of training enhances speed, power, and area with minimal accuracy loss.
Improved sparse Gaussian processes using structured scaling matrices and Power-EP framework.
problem Scaling Gaussian processes for large datasets.
method Structured diagonal scaling matrix and Power-EP framework.
result Structured approximations improve performance without increasing computational cost.
We propose an explicit recursive method to approximate a power-law with a finite sum of weighted exponentials. Applications to moving averages with long memory are discussed in relationship with stochastic volatility models.
A new test method improves goodness-of-fit tests for copulas.
problem Developing robust tests for copula goodness-of-fit.
method Binary Expansion Approximation of UniformiTY (BEAUTY) and Binary Expansion Adaptive Symmetry Test (BEAST).
result The BEAST method improves empirical power against various alternatives.
INNs can approximate diverse functions despite layer restrictions.
problem Can INNs approximate sufficiently diverse functions?
method Developed a theoretical framework based on differential geometry to simplify the approximation problem of diffeomorphisms.
result INNs have the universal approximation property.
Study reveals Transformer's expressive power and mechanisms.
problem Understanding the approximation properties of Transformer for sequence modeling.
method Systematic study of Transformer's components and their combined effects, establishing approximation rates.
result Reveals roles of critical parameters in Transformer, such as number of layers and attention heads.
Gaussian processes (GPs) are flexible distributions over functions that enable high-level assumptions about unknown functions to be encoded in a parsimonious, flexible and general way. Although elegant, the application of GPs is limited by computational and analytical intractabilities that arise when data are sufficien…
Improved bounds on neural network expressivity.
problem Understanding neural network expressivity and approximation capabilities.
method Improved bounds on the maximal number of linear regions of ReLU-networks.
result New insights into the expressivity of neural networks.
Deep neural networks can approximate complex functions through repeated compositions of a fixed-size ReLU network.
problem Understanding the expressive power of deep neural networks through function compositions.
method Demonstrated the surprising expressive power of repeated compositions of a single fixed-size ReLU network.
result Repeated compositions of a single fixed-size ReLU network can approximate 1-Lipschitz continuous functions on [0,1]d with an error O(r−1/d). CTT compresses samples to test distributions near-linearly, outperforming existing methods.
problem Efficiently testing distributions with high power and near-linear runtime.
method Sample compression followed by permutation testing.
result CTT achieves near-linear runtime while maintaining high statistical power.
The approximation power of general feedforward neural networks with piecewise linear activation functions is investigated. First, lower bounds on the size of a network are established in terms of the approximation error and network depth and width. These bounds improve upon state-of-the-art bounds for certain classes o…
A new method improves convergence in low-rank approximation.
problem Efficiently solving large-scale numerical linear algebra problems.
method Error-Powered Sketched Inverse Iteration (EPSI) Method.
result Convergence rate improves at least linearly with sketch size.
Randomly initialized ReLU networks of depth two can approximate smooth functions well.
problem Approximation power of two-layer networks of random ReLUs.
method Harmonic analysis and ridgelet representation theory for upper bounds, dimensionality arguments for lower bounds.
result Near-matching upper and lower bounds for L2-approximation and Sobolev norms. PLN-Nets with two linear layers and parallel LN achieve universal approximation.
problem Limitations of standard neural network architectures in universal approximation.
method Introduced PLN-Nets combining two linear layers with parallel LN.
result PLN-Nets achieve universal approximation, while standard LN has limited power.
New network approximates functions with error decreasing with network width and depth.
problem Approximating functions with high-dimensional data.
method Floor-ReLU networks with specific width and depth.
result Approximation error decreases as network width and depth increase.
The paper argues for interpreting neural networks as approximating the true posterior, enhancing in-context learning.
problem The limitations of traditional MLE interpretation in large-scale, single-epoch training setups.
method Demonstrates the power of interpreting neural networks as approximations of the true posterior, using experiments to predict generalizations.
result Models become robust in-context learners by effectively composing knowledge from their training data, revealing surprising generalizations.
Paper uses Gaussian processes to solve AC-OPF with renewable uncertainty.
problem Optimizing power grids with fluctuating renewable sources.
method Data-driven approach using Gaussian processes.
result Efficiently solves chance-constrained AC-OPF with uncertainty.
We statistically investigate the distribution of share price and the distributions of three common financial indicators using data from approximately 8,000 companies publicly listed worldwide for the period 2004-2013. We find that the distribution of share price follows Zipf's law; that is, it can be approximated by a …
Deep RL improves power control and scheduling for wireless multicast systems.
problem Scalable power control and scheduling for wireless multicast networks.
method Deep reinforcement learning with function approximation using a deep neural network.
result Deep RL can learn optimal power control policies for large systems.
Power quandles improve group invariants and allow group presentations.
problem Understanding and classifying groups using algebraic structures.
method Introducing power quandles, which retain conjugation and power maps, and showing their effectiveness in group theory.
result Power quandles determine central quotients and centers of groups, and can approximate any group.
We derive the implied volatility estimation formula in European power call options pricing, where the payoff functions are in the form of V=(STα−K)+ and V=(STα−Kα)+ (α>0)respectively. Using quadratic Taylor approximations, We develop the computing formula of implied volatility in European power call op…
New method uses kernel methods to approximate ground states of quantum Hamiltonians efficiently.
problem Approximating ground states of quantum Hamiltonians using neural networks is computationally expensive.
method Introduces a statistical learning approach using kernel methods to make optimization trivial.
result Ground state properties of arbitrary gapped quantum Hamiltonians can be reached with polynomial resources.
The paper analyzes the variance of different shuffling methods in stochastic gradient descent.
problem Understanding the variance of different shuffling methods in stochastic gradient descent.
method Power spectral density analysis to study the noise sequences of stochastic gradients.
result The stationary variances of iterates decrease in the order of SGD, SGD-RR, and SGD-SO.
Optimizes power systems with energy storage under uncertainty using scenario-based method.
problem Optimizing power systems with energy storage, intermittent renewable generation, and uncontrollable loads under uncertainty.
method Developed a novel solution method based on scenario optimization and strategic sampling to solve the chance-constrained optimal power system operation problem.
result The strategic sampling method significantly improves computational efficiency and data-driven convex approximation of power flow.
Shampoo optimizes preconditioners for faster convergence in machine learning.
problem Improving convergence speed in machine learning optimization.
method Explicit connection between Shampoo's Kronecker product approximation and optimal matrix approximations.
result The square of Shampoo's approximation is equivalent to a single power iteration step for optimal Kronecker product approximation.
Transformers model contextual relations using probabilistic measures, revealing their expressive power.
problem Lack of clear understanding of Transformer's ability to model contextual relations.
method Introduced a measure-theoretic framework connecting softmax attention and entropy-regularized optimal transport.
result Transformer architectures can approximate arbitrary contextual relations, and the choice of normalization affects how these relations are represented.
In this paper, from a theoretical perspective, we study how powerful graph neural networks (GNNs) can be for learning approximation algorithms for combinatorial problems. To this end, we first establish a new class of GNNs that can solve a strictly wider variety of problems than existing GNNs. Then, we bridge the gap b…
Quantum models can approximate any function if data encoding allows for a rich enough frequency spectrum.
problem Theoretical properties of quantum machine learning models, particularly their expressive power.
method Investigated how data encoding affects the expressive power of parametrized quantum circuits.
result Quantum models can access increasingly rich frequency spectra by repeating data encoding gates, potentially making them universal function approximators.
Graph Neural Networks (GNNs) have achieved much success on graph-structured data. In light of this, there have been increasing interests in studying their expressive power. One line of work studies the capability of GNNs to approximate permutation-invariant functions on graphs, and another focuses on the their power as…
This paper investigates the approximation power of three types of random neural networks: (a) infinite width networks, with weights following an arbitrary distribution; (b) finite width networks obtained by subsampling the preceding infinite width networks; (c) finite width networks obtained by starting with standard G…
Novel algorithm for Markov decision processes using rank-one approximation.
problem Solving planning and learning problems of Markov decision processes.
method Policy iteration with rank-one approximation of transition probability matrix.
result The proposed algorithm consistently outperforms first-order algorithms and their accelerated versions.
Low-rank structure have been profoundly studied in data mining and machine learning. In this paper, we show a dense matrix X's low-rank approximation can be rapidly built from its left and right random projections Y1=XA1 and Y2=XTA2, or bilateral random projection (BRP). We then show power scheme can further…
The paper investigates heavy-tailed behavior in offline SGD, showing it approximates power-law tails.
problem Understanding heavy-tailed behavior in offline (multi-pass) SGD with finite data.
method Proves nonasymptotic Wasserstein convergence bounds for offline SGD to online SGD.
result Offline SGD exhibits approximate power-law tails as the number of data points increases.
New analysis shows RPE-based Transformers can't approximate all functions.
problem Understanding the limitations of RPE-based Transformers in approximating continuous functions.
method Mathematical analysis and development of a novel attention module (URPE) to overcome limitations.
result RPE-based Transformers can't approximate all continuous sequence-to-sequence functions, even with depth and width.
GroupSort neural networks can approximate Lipschitz continuous functions.
problem Understanding and improving the expressive power of neural networks with Lipschitz constraints.
method Introduced and studied GroupSort neural networks with constraints on weights, proving their ability to approximate Lipschitz continuous functions.
result GroupSort networks can represent any Lipschitz continuous piecewise linear functions and are well-suited for approximating general Lipschitz continuous functions.
Geometric GNNs improve graph discrimination through GWL.
problem Discriminating geometric graphs embedded in Euclidean space.
method Proposed a geometric version of the Weisfeiler-Leman test (GWL) for geometric graphs.
result Characterized the expressive power of geometric GNNs based on physical symmetries.
Deep residual networks can approximate any continuous function using control theory.
problem Universal approximation capabilities of deep residual neural networks.
method Relating residual networks to control systems and using Lie algebraic techniques.
result Deep residual networks with adequately deep layers can approximate any continuous function on a compact set.
In this paper, we develop an online method that leverages machine learning to obtain feasible solutions to the AC optimal power flow (OPF) problem with negligible optimality gaps on extremely fast timescales (e.g., milliseconds), bypassing solving an AC OPF altogether. This is motivated by the fact that as the power gr…
In this paper we present an analysis of power law statistics on land markets. There have been no other studies that have analyzed power law statistics on land markets up to now. We analyzed a database of the assessed value of land, which is officially monitored and made available to the public by the Ministry of Land, …
We consider a multicast scheme recently proposed for a wireless downlink in [1]. It was shown earlier that power control can significantly improve its performance. However for this system, obtaining optimal power control is intractable because of a very large state space. Therefore in this paper we use deep reinforceme…
PNCs balance tractability and expressiveness in probabilistic modeling.
problem Balancing tractability and expressiveness in probabilistic models.
method Introduce probabilistic neural circuits (PNCs) as a mix of Bayesian networks and neural networks.
result PNCs are powerful function approximators.
Paper compares expressive power of GNNs, proving approximation guarantees for practical architectures.
problem Understanding the expressive power of Graph Neural Networks (GNNs).
method Theoretical framework comparing invariant and equivariant GNNs, proving approximation guarantees for practical architectures.
result Folklore Graph Neural Networks (FGNN) are the most expressive architectures for a given tensor order.
Many biological learning systems such as the mushroom body, hippocampus, and cerebellum are built from sparsely connected networks of neurons. For a new understanding of such networks, we study the function spaces induced by sparse random features and characterize what functions may and may not be learned. A network wi…
The holonomic approximation lemma of Eliashberg and Mishachev is a powerful tool in the philosophy of the h−principle. By carefully keeping track of the quantitative geometry behind the holonomic approximation process, we establish several refinements of this lemma. Gromov's idea from convex integration of working on…
Paper compares ML models for fast power system contingency case identification.
problem Identifying critical power system states quickly.
method Comparison of regression and classification ML models.
result MLPs most suitable for fast contingency case prediction.
Variational inference is a powerful tool for approximate inference, and it has been recently applied for representation learning with deep generative models. We develop the variational Gaussian process (VGP), a Bayesian nonparametric variational family, which adapts its shape to match complex posterior distributions. T…
Paper develops polynomial approximations for complex probability densities.
problem Approximating high-dimensional concentrated probability densities.
method Tensor-product spectral polynomials and KR rearrangements.
result Efficient approximation of complex densities using composite maps.