Method generates dense fields from sparse measurements without needing spatial statistics or examples.
problem Generating dense physical fields from sparse measurements.
method Introduces a differentiable numerical simulator into neural network training.
result Superior results on fluid mechanics problems compared to statistical and neural network methods.
The paper explores graphons of line graphs from sparse finite graphs.
problem Estimating graph limits from sparse finite graphs.
method Mapping finite graphs to their line graphs and analyzing graphs with the square-degree property.
result Graphons of line graphs can distinguish between sparse graphs like star graphs and superlinear preferential attachment graphs.
Using a Bayesian approach, we consider the problem of recovering sparse signals under additive sparse and dense noise. Typically, sparse noise models outliers, impulse bursts or data loss. To handle sparse noise, existing methods simultaneously estimate the sparse signal of interest and the sparse noise of no interest.…
This paper explores loss landscapes of sparse neural networks, finding unique characteristics compared to dense networks.
problem Understanding the loss landscape of sparse neural networks, especially one-hidden-layer networks.
method Analyzes sparse networks with dense and sparse final layers, focusing on linear and non-linear models.
result Sparse networks can have no spurious valleys under certain conditions, but spurious valleys and minima can exist for wide sparse networks.
Finding "densely connected clusters" in a graph is in general an important and well studied problem in the literature \cite{Schaeffer}. It has various applications in pattern recognition, social networking and data mining \cite{Duda,Mishra}. Recently, Ames and Vavasis have suggested a novel method for finding cliques i…
Generative model captures hubs and dense communities in social networks.
problem Capturing both hubs and dense communities in social networks.
method Graphon mixture model with a new condition on sparse graphs.
result Estimation of hub normalized degree and graphon for sparse components.
Sparse Hopfield model improves memory retrieval with fewer connections.
problem Memory retrieval efficiency with fewer connections.
method Sparse extension of Hopfield model, derived from sparse entropic regularizer.
result Sparse Hopfield model achieves tighter error bounds and better performance.
Random extrapolation speeds up coordinate descent for sparse and dense data.
problem Efficiently solving primal-dual coordinate descent for sparse and dense data.
method Adapts to sparsity and uses large step sizes for dense data, proving linear convergence under metric subregularity.
result Linear convergence under metric subregularity and optimal sublinear convergence rates in general convex-concave problems.
New GPU kernels boost deep learning speed and memory efficiency.
problem Sparse deep learning matrices are not well-suited for existing sparse kernels.
method Identified favorable properties of sparse matrices from deep learning, developed high-performance GPU kernels for sparse matrix operations.
result 27% of single-precision peak performance on Nvidia V100 GPUs achieved with new kernels.
Transforming sparse outcomes into dense process rewards for efficient reinforcement learning.
problem Training RL policies to maximize sparse outcomes.
method Incentivizing policy matching state-action visitations of successful episodes.
result Significantly faster RL finetuning performance.
Predicts food ingredient amounts from images.
problem Predicting relative amounts of ingredients from food images.
method Proposes two deep learning models for sparse and dense predictions, with semi-automatic data pre-processing.
result Encouraging experimental results on a recipe dataset.
Ranky solves SVD for large sparse matrices in distributed systems.
problem Rank problem in large sparse matrices for SVD.
method Distributed approach to solve rank problem.
result Recovers SVD with negligible error for large sparse matrices.
Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this advantage does not hold during training. We propose techniques to enforce sparsen…
New models explain residual and dilated dense neural networks using sparse coding.
problem Lack of theoretical understanding of residual and dilated dense neural networks.
method Proposed Res-CSC and MSD-CSC models, derived mathematical relationships, implemented ISTA.
result Mathematical understanding of residual and dilated dense neural networks.
Sparse Transformers can approximate dense Transformers with only O(n) connections.
problem Can sparse Transformers approximate arbitrary sequence-to-sequence functions?
method Proposed sufficient conditions for universal approximation and proved that sparse Transformers with O(n) connections can approximate dense models.
result Sparse Transformers with O(n) connections can approximate the same function class as dense models with n^2 connections.
Most artificial networks today rely on dense representations, whereas biological networks rely on sparse representations. In this paper we show how sparse representations can be more robust to noise and interference, as long as the underlying dimensionality is sufficiently high. A key intuition that we develop is that …
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.
New estimator learns symmetric dynamics from few observations.
problem Learning parameters of stochastic linear dynamics from limited data.
method Method of moments estimator using T=O(logN) observations. result Achieves small maximum element-wise error on symmetric matrices.
The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning edges from the underlying topology. The resulting neural network is known as a …
Sparse deep neural networks(DNNs) are efficient in both memory and compute when compared to dense DNNs. But due to irregularity in computation of sparse DNNs, their efficiencies are much lower than that of dense DNNs on regular parallel hardware such as TPU. This inefficiency leads to poor/no performance benefits for s…
SpaPool combines dense and sparse techniques for efficient graph pooling.
problem Efficiently processing large graphs in graph neural networks.
method Adaptive clustering of graph vertices into clusters.
result SpaPool outperforms existing methods on small-scale graphs.
We present and analyze a simple, two-step algorithm to approximate the optimal solution of the sparse PCA problem. Our approach first solves a L1 penalized version of the NP-hard sparse PCA optimization problem and then uses a randomized rounding strategy to sparsify the resulting dense solution. Our main theoretical r…
Sparse butterfly network replaces dense layers in neural networks, improving expressibility and performance.
problem Improving expressibility and performance of neural networks with dense layers.
method Replacing dense layers with a butterfly network architecture.
result The proposed architecture significantly reduces the number of weights from quadratic to nearly linear, with comparable or better performance.
New method uses temperature to control sparse MoE convergence rates.
problem Sparse MoE convergence rates are slow due to temperature interactions.
method Proposes a novel activation gate to improve convergence rates.
result Improved convergence rates to polynomial rates via novel gate.
Method trains sparse neural networks without sacrificing accuracy.
problem Training sparse neural networks limits model size.
method Updates sparse network topology during training.
result Requires fewer FLOPs to achieve accuracy.
A new method for clustering high-dimensional data into subspaces efficiently and accurately.
problem Inaccurate clustering due to poor intra-subspace similarity in existing methods.
method Iterative Maximum Correlation (IMC) for affinity matrix learning and Piecewise Correlation Estimation (PCE) for densification.
result SDSC framework improves clustering accuracy and efficiency for large-scale data.
We propose an efficient algorithm for sparse signal reconstruction problems. The proposed algorithm is an augmented Lagrangian method based on the dual sparse reconstruction problem. It is efficient when the number of unknown variables is much larger than the number of observations because of the dual formulation. More…
Sparse Vision MoE matches dense networks in image recognition while using less compute.
problem Scaling vision models efficiently in computer vision.
method Vision MoE (V-MoE) - a sparse version of Vision Transformer.
result V-MoE matches state-of-the-art dense networks in image recognition with half the compute.
New algorithm speeds up regression tasks for large datasets.
problem Efficiently solving optimization and regression tasks with large datasets.
method Iterative Hessian Sketching (IHS) combined with matrix sketching techniques.
result Significantly faster algorithms for constrained regression tasks.
Four algorithms improve sparse tensor BR1Approx with theoretical guarantees.
problem Sparse tensor best rank-1 approximation.
method Four approximation algorithms exploiting multilinearity and sparsity.
result Theoretical worst-case approximation lower bounds for all algorithms.
While sparse inverse covariance matrices are very popular for modeling network connectivity, the value of the dense solution is often overlooked. In fact the L2-regularized solution has deep connections to a number of important applications to spectral graph theory, dimensionality reduction, and uncertainty quantificat…
Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by operating on a sparse representation of graph adjacency matrices. As we look to scale up these models using custom hardware, a natural assum…
Sparse neural networks can match dense models on Lipschitz functions.
problem Sparse networks are more efficient but lack theoretical guarantees.
method Formal model of sparse networks, LSH-based routing function, Lipschitz function approximation.
result Sparse networks can approximate dense networks on Lipschitz functions.
The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning edges from the underlying topology. The resulting neural network is known as a …
We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse momentum, an algorithm which uses exponentially smoothed gradients (momentum) to…
This work proposes a method to learn sparse representations that are more efficient for large-scale data retrieval.
problem Efficient retrieval of high-dimensional representations from large databases is computationally challenging.
method The approach minimizes the number of floating-point operations (FLOPs) by learning sparse embeddings with uniform non-zero entries.
result The proposed method achieves a similar or better speed-vs-accuracy tradeoff compared to existing baselines.
New insights link diverse statistical problems via secret leakage planted clique.
problem Statistical-computational gaps in inference problems.
method Secret leakage planted clique as a new hardness assumption for reductions.
result Establishes tight statistical-computational tradeoffs for various problems.
Chromatic Learning reduces feature dimensions for sparse datasets.
problem Sparse, high-dimensional data challenges traditional learning methods.
method Graph coloring over co-occurrence graph to create dense feature representation.
result Compresses sparse datasets significantly while maintaining model accuracy.
Recently, the decentralized optimization problem is attracting growing attention. Most existing methods are deterministic with high per-iteration cost and have a convergence rate quadratically depending on the problem condition number. Besides, the dense communication is necessary to ensure the convergence even if the …
This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and a universality principle for these gaps. A main feature of our approach is to ma…
Busemann points are sparse in Teichmüller spaces.
problem Characterizing the limits of geodesic rays in Teichmüller spaces.
method Proof of nowhere density of Busemann points in horoboundaries.
result Teichmüller metrics lack non-positive curvature.
Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One approach to overcoming this limit is the design of sparse neural networks, which ca…
Efficient sparse modern Hopfield models are introduced for memory retrieval and learning tasks.
problem Efficient modern Hopfield models for memory retrieval and learning tasks.
method Nonparametric interpretation of Hopfield models as a regression problem.
result Sparse-structured modern Hopfield models with sub-quadratic complexity.
The paper studies PCA of probability measures with varying sample sizes and finds optimal convergence rates.
problem PCA of multiple probability measures with varying sample sizes.
method Double asymptotic regime analysis with convergence rates n−1/2+m−α for empirical covariance and PCA risk. result Optimal convergence rates for empirical covariance and PCA risk in the dense regime are proven.
This paper establishes conditions for sparse signal recovery with sparse measurements.
problem Recovering the support of a sparse signal using noisy projections with sparse measurement matrices.
method Establishes sufficient conditions for successful sparse recovery using sparse measurement matrices.
result A phase transition threshold for sparse recovery in the sparse setting is discovered, revealing a trade-off between sampling complexity and measurement sparsity.
SKI accelerates GP inference with sparse grids to handle higher dimensions.
problem SKI scales poorly in high dimensions due to dense grid size.
method Sparse grids within SKI framework, novel matrix-vector multiplication algorithm.
result SKI can be scaled to higher dimensions while maintaining accuracy.
CRL framework groups features for multivariate learning with sparse and dense problems.
problem Sparse and dense problems in supervised multivariate learning.
method Clustered reduced-rank learning (CRL) with joint matrix regularizations.
result CRL framework is more interpretable and relaxes sparsity assumption.
In this paper, we give a new generalization error bound of Multiple Kernel Learning (MKL) for a general class of regularizations, and discuss what kind of regularization gives a favorable predictive accuracy. Our main target in this paper is dense type regularizations including \ellp-MKL. According to the recent numeri…