Recovering edge activities from node activity data in temporal networks.
problem Recovering lost edge activity data from aggregated node activity data in temporal networks.
method Analyzing the relationship between edge activity and node activity data, using both theoretical and empirical methods to show recovery is possible and under what conditions.
result Recovery of edge activities from node activities is possible with surprising accuracy, even when network density increases.
New method recovers matrix column space with active sampling for better results.
problem Recovering column space of partially observed matrices with limited data.
method Alternating minimization with active sampling strategy.
result Active sampling improves convergence to true column space with higher probability.
Active seriation recovers item order from noisy pairwise similarity measurements.
problem Recovering an unknown item ordering from noisy pairwise similarity measurements.
method Proposes an active seriation algorithm that provably recovers the latent ordering with high probability.
result Establishes optimal performance guarantees for successful recovery under a uniform separation condition.
Locally adaptive activation functions boost deep and physics-informed neural networks.
problem Improving the performance and training speed of deep and physics-informed neural networks.
method Layer-wise and neuron-wise locally adaptive activation functions with a slope recovery term.
result The proposed methods accelerate convergence and reduce training cost.
D-CSC framework reveals how ReLU activation functions recover activation paths in neural networks.
problem Understanding how ReLU activation functions recover activation paths in neural networks.
method Deep Convolutional Sparse Coding (D-CSC) framework, omitting dictionary learning, to analyze activation paths.
result Uniform guarantees for recovery of true activation paths with high probability for greater activation densities.
Reveals the first layer of deep networks with high activation thresholds.
problem Learning guarantees for deep neural networks with multiple layers.
method Strengthening parameter recovery guarantees for deep networks with a high threshold assumption.
result Reveals the first layer of a deep neural network under specific activation conditions.
Proposes an offline active learning method for graphs.
problem Active learning on graphs where labeling is expensive.
method Two-stage biased sampling strategy considering informativeness and representativeness.
result Establishes a theoretical relationship between generalization error and number of nodes selected.
Optimal sparse recovery with decision stumps achieves strong feature selection guarantees.
problem Sparse recovery of active features from high-dimensional data.
method Analysis of single-depth decision trees (decision stumps) for feature selection in linear regression.
result Tight sample performance guarantees for O(slogp), improving upon previous bounds. In this paper, we consider the problem of recovering a sparse signal based on penalized least squares formulations. We develop a novel algorithm of primal-dual active set type for a class of nonconvex sparsity-promoting penalties, including ℓ0, bridge, smoothly clipped absolute deviation, capped ℓ1 and mini…
The paper provides recovery guarantees for CNNs with multiple kernels under polynomial sample and computational complexities.
problem Parameter recovery for non-overlapping CNNs with multiple kernels.
method Showed local strong convexity of squared loss for most popular activations, used tensor methods for initialization, and proved convergence of gradient descent.
result Gradient descent following tensor initialization converges to the global optimal with polynomial time complexity.
This work optimizes clustering with adaptive queries to minimize disagreements.
problem Minimizing disagreements in clustering with adaptive similarity queries.
method Active learning algorithms and information-theoretical bounds.
result Achieves an almost optimal trade-off between queries and clustering error.
Flat minima lead to better generalization in low-rank matrix recovery models.
problem Understanding why flat minima generalize well in overparameterized models.
method Analysis of overparameterized matrix and bilinear sensing, robust PCA, covariance matrix estimation, and neural networks with quadratic activation functions.
result Flat minima, measured by the trace of the Hessian, exactly recover the ground truth in low-rank matrix recovery models under standard statistical assumptions.
New method selects variables in groups with few nonzeros, improving support recovery.
problem Structured variable selection with sparse patterns across groups.
method Composite norm and proximal algorithm for exclusive group sparsity.
result Asymptotic consistency in signed support recovery under conventional assumptions.
In this paper, we propose majority voting neural networks for sparse signal recovery in binary compressed sensing. The majority voting neural network is composed of several independently trained feedforward neural networks employing the sigmoid function as an activation function. Our empirical study shows that a choice…
The measurement and analysis of Electrodermal Activity (EDA) offers applications in diverse areas ranging from market research, to seizure detection, to human stress analysis. Unfortunately, the analysis of EDA signals is made difficult by the superposition of numerous components which can obscure the signal informatio…
Study improves distributed linear estimation under adversarial conditions.
problem Mean estimation of a random vector with adversarial measurements and asynchrony.
method Two-timescale ℓ1-minimization algorithm with tight convergence rates.
result Unified finite-time characterization of robustness, identifiability, and statistical efficiency.
Recovery of low-rank matrices has recently seen significant activity in many areas of science and engineering, motivated by recent theoretical results for exact reconstruction guarantees and interesting practical applications. A number of methods have been developed for this recovery problem. However, a principled meth…
In this paper, we consider regression problems with one-hidden-layer neural networks (1NNs). We distill some properties of activation functions that lead to local strong convexity in the neighborhood of the ground-truth parameters for the 1NN squared-loss objective. Most popular nonlinear activation function…
Study of active learning in geometric block model for community detection.
problem Active learning for community detection in geometric block model.
method Proposed two active learning algorithms combining motif-counting with label query policies.
result Sampling labels of a vanishingly small fraction of nodes is sufficient for exact recovery.
Full-batch GD outperforms one-pass SGD in learning a single-index model with quadratic activation.
problem Learning a single-index model with quadratic activation using gradient descent.
method Full-batch gradient descent compared to one-pass stochastic gradient descent (SGD) on a correlation loss.
result Full-batch GD requires only n≃d samples for strong recovery, while one-pass SGD requires n≳dlogd samples. New algorithms recover clusters with minimal queries, connecting margins to recoverability.
problem Active cluster recovery with oracle queries for minimal cost.
method Introducing margin-based clustering, designing algorithms for various spaces.
result Achieve O(logn) queries for general pseudometric spaces and convex clusters. Study on neural network dynamics in high dimensions with quadratic activation.
problem Understanding training dynamics in overparameterized neural networks.
method Derivation of gradient flow equations and analysis under l2-regularization.
result Characterization of estimator performance and spectral properties in the high-dimensional limit.
New SAE algorithm proves feature recovery for LLMs with theoretical guarantees.
problem Achieving interpretable features in large language models (LLMs).
method Proposed a statistical framework and bias adaptation technique for sparse autoencoders (SAEs).
result Proved correct recovery of all monosemantic features under specific data sampling.
Standard compressive sensing results state that to exactly recover an s sparse signal in R^p, one requires O(s. log(p)) measurements. While this bound is extremely useful in practice, often real world signals are not only sparse, but also exhibit structure in the sparsity pattern. We focus on group-structured patterns …
Deep learning identifies functional primitives in stroke rehabilitation.
problem Measuring the necessary dose of rehabilitation training for stroke recovery.
method Automatic identification of functional primitives using IMUs and deep learning.
result Convolutional neural network achieved 70% accuracy in primitive classification.
Exact cluster recovery with same-cluster queries for arbitrary ellipsoidal clusters.
problem Recovering clusters from same-cluster queries in arbitrary ellipsoidal clusters.
method Relaxing spherical k-means assumption to arbitrary ellipsoidal clusters, designing an algorithm with logarithmic query complexity. result Exact recovery of clusters using O(k3lnklnn) queries and ildeO(kn+k3) time. The paper studies recovery problems for ReLU networks, providing theoretical results on dictionary learning and robust signal recovery.
problem Recovery of latent vectors and signal from noisy nonlinear sketches of ReLU networks.
method Theoretical analysis of dictionary learning and robust signal recovery problems using ReLU networks.
result Generalized LASSO algorithm can recover signals with a specified error bound under certain conditions.
Study on Gaussian-width complexity on statistical manifolds and its applications in learning and recovery.
problem Understanding the geometry of statistical manifolds and its implications for learning and recovery.
method Analysis of Fisher width and inverse-Fisher width, proving their complementary roles and establishing a relation between them.
result Established a sharp relation between Fisher width and inverse-Fisher width, showing they cannot reduce relative to Euclidean scale.
Study shows overparameterization helps shallow neural networks recover signals in high dimensions.
problem Signal recovery in shallow neural networks with overparameterization.
method Gradient flow on population risk, Gaussian distribution assumption, high-dimensional limit analysis.
result Minimal overparameterization is sufficient for strong recovery of signals.
Hybrid-MST improves preference aggregation from sparse data.
problem Recovering ratings from sparse and noisy pairwise data.
method Bayesian optimization and Bradley-Terry model for utility function, Gaussian-Hermite quadrature for EIG estimation, hybrid sampling strategy.
result Hybrid-MST outperforms state-of-the-art methods in preference aggregation.
Study exact partition recovery with same-cluster oracle, bounded error.
problem Exact recovery of partitions with same-cluster oracle in adversarial error.
method Novel connection to correlation clustering, Rényi-Ulam framework, upper and lower bounds, randomized algorithm analysis, adaptivity-query complexity study.
result Upper and lower bounds on worst-case query complexity, expected performance bounds of randomized algorithm.
GNMR controls runtime stability in low-precision language model training.
problem Efficient low-precision training faces numerical risks at specific operators.
method GNMR compares gradient norms to historical means, applying bounded recovery actions.
result GNMR preserves high-fidelity quality with sparse, budgeted recovery.
In applications ranging from communications to genetics, signals can be modeled as lying in a union of subspaces. Under this model, signal coefficients that lie in certain subspaces are active or inactive together. The potential subspaces are known in advance, but the particular set of subspaces that are active (i.e., …
Causal inference concerns the identification of cause-effect relationships between variables, e.g. establishing whether a stimulus affects activity in a certain brain region. The observed variables themselves often do not constitute meaningful causal variables, however, and linear combinations need to be considered. In…
Gradient-free method reduces dimensionality without gradients for expensive models.
problem Reducing high-dimensional input spaces for expensive models without gradient information.
method Fully Bayesian, gradient-free approach using Gaussian processes.
result Improves active subspace recovery and probabilistic prediction accuracy with limited data.
Spike and Slab priors have been of much recent interest in signal processing as a means of inducing sparsity in Bayesian inference. Applications domains that benefit from the use of these priors include sparse recovery, regression and classification. It is well-known that solving for the sparse coefficient vector to ma…
We consider the problem of estimating the underlying graph associated with a Markov random field, with the added twist that the decoding algorithm can iteratively choose which subsets of nodes to sample based on the previous samples, resulting in an active learning setting. Considering both Ising and Gaussian models, w…
Optimizing post-crisis recovery in scale-free networks by stimulating high-degree nodes.
problem Determining the most cost-effective nodes to stimulate in scale-free networks for economic recovery.
method Utilized the Ising model to analyze metastable features and costs of stimulating nodes in scale-free networks.
result Stimulation of high-degree nodes is more cost-effective in scale-free networks compared to regular networks.
Active subspaces on Riemannian manifolds generalize Euclidean principles.
problem Understanding how scalar-valued quantities change over Riemannian manifolds.
method Generalization of active subspaces from Euclidean to Riemannian spaces using parallel transport.
result The method provides a new way to study scalar-valued quantities on manifolds, differing from extrinsic approaches.
In order to model volatile real-world network behavior, we analyze phase-flipping dynamical scale-free network in which nodes and links fail and recover. We investigate how stochasticity in a parameter governing the recovery process affects phase-flipping dynamics, and find the probability that no more than q% of nodes…
Paper proposes a neural network for sparse recovery using Laplace techniques.
problem Sparse recovery from compressed measurements.
method Designing a neural network to compute the centroid of a polytope.
result Analytical computation of volume and centroid enables efficient sparse recovery.
This paper classifies typhoon damage features using aerial photography.
problem Typhoon damages and slow recovery times.
method Aerial photography for classification of eight classes including land covers and disaster areas.
result Visualize and explain typhoon disaster features using convolutional activation maps.
New algorithm speeds up spike sorting for large datasets.
problem Numerical complexity limits processing large scale neuroscience datasets.
method Windowed active set Lasso algorithm for convolutional spike sorting.
result Linear complexity ensures scalability and opens online sorting.
Exact inversion of deep ReLU models is possible for single layers and with high probability for deep models.
problem Inverting deep generative models with ReLU activations.
method Theoretical analysis and algorithms for exact inversion of single and multiple layers of deep generative models.
result Exact recovery of latent codes is possible for single layers and with high probability for deep models, under certain conditions.
Gradient descent recovers neural networks with cross entropy.
problem Recovering weights of one-hidden-layer neural networks from labeled data.
method Empirical risk minimization using cross entropy with gradient descent.
result Gradient descent converges linearly to a close approximation of the ground truth weights.
Study on neural networks with quadratic activation functions, focusing on optimization and generalization.
problem Understanding the dynamics and generalization of neural networks with quadratic activation in the over-parametrized regime.
method Teacher-student scenario, empirical loss landscape analysis, gradient descent dynamics, numerical experiments.
result Conditions for the neural network to recover the teacher and achieve small generalization error.
New model improves community detection in networks with strong assortativity.
problem Classic SBMs fail to recover assortative communities in networks with reduced information.
method Introduced a constrained SBM with strong assortativity constraints and efficient algorithms.
result Significant boost in community recovery capabilities, especially close to information-theoretic threshold.
Active-set algorithm improves Cox regression for shape-restricted covariates.
problem Improving Cox regression for shape-restricted covariates.
method Shape-restricted inference using active-set optimization for spline basis expansion.
result Active-set algorithm produces accurate linear covariate effect estimates.