Quantized neural networks can represent all fixed-point functions under certain conditions.
problem Expressive power of quantized neural networks under fixed-point arithmetic.
method Analyzing necessary and sufficient conditions for quantized networks to represent all fixed-point functions.
result Various popular activation functions satisfy the sufficient condition for representing all fixed-point functions.
Active learning can't improve over passive in certain settings.
problem Active learning vs. passive learning in nonparametric settings.
method Analyzing margin conditions and their effects on active learning performance.
result Nuances in margin conditions determine whether active learning can outperform passive learning.
We propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each lay…
Active learning seeks to build the best possible model with a budget of labelled data by sequentially selecting the next point to label. However the training set is no longer \textit{iid}, violating the conditions required by existing consistency results. Inspired by the success of Stone's Theorem we aim to regain cons…
Develops wavelet-based neural network approximation theory.
problem Analyzing neural network approximation capabilities over various activation functions.
method Wavelet frame theory on spaces of homogeneous type, sufficient conditions for approximation, error estimates.
result Derives sufficient conditions for neural networks to approximate any functions in a given space, including non-smooth activations.
In the high-dimensional regression model a response variable is linearly related to p covariates, but the sample size n is smaller than p. We assume that only a small subset of covariates is `active' (i.e., the corresponding coefficients are non-zero), and consider the model-selection problem of identifying the a…
Study learns a neuron with non-monotonic activation functions.
problem Learning a single neuron with non-monotonic activation functions.
method Gradient descent (GD) with conditions on activation function and input distribution.
result Learnability of non-monotonic activation functions is established without monotonicity assumption.
Develops CLDS models to model neural activity with nonlinear dynamics.
problem Complex, nonlinear dynamics in neural population activity.
method Conditionally Linear Dynamical System (CLDS) models using Gaussian Process (GP) priors.
result CLDS models can perform well even in data-limited conditions.
In this work we investigate intra-day patterns of activity on a population of 7,261 users of mobile health wearable devices and apps. We show that: (1) using intra-day step and sleep data recorded from passive trackers significantly improves classification performance on self-reported chronic conditions related to ment…
Discriminative active learning reduces data annotation costs for domain adaptation.
problem Conditional shift problem hinders domain adaptation between related but different domains.
method Three-stage active adversarial training: invariant feature space learning, uncertainty and diversity criteria, re-training with queried labels.
result Empirical comparisons show the proposed approach is more effective than existing methods.
We consider active learning with logged data, where labeled examples are drawn conditioned on a predetermined logging policy, and the goal is to learn a classifier on the entire population, not just conditioned on the logging policy. Prior work addresses this problem either when only logged data is available, or purely…
S2D selectively decays large singular values to improve quantization of neural activations.
problem Large activation outliers in transformer models cause accuracy drops during quantization.
method Selective Spectral Decay (S2D) that surgically regularizes only the largest singular values. result Significantly reduces activation outliers and produces well-conditioned representations.
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…
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.
VSD efficiently learns conditional distributions for combinatorial designs.
problem Learning conditional distributions for rare combinatorial designs.
method Variational Search Distributions (VSD) using variational inference.
result VSD outperforms existing methods on real sequence-design problems.
Efficient algorithm for halfspaces with specific noise conditions.
problem Learning halfspaces with Massart and Tsybakov noise.
method PAC active learning algorithm for d-dimensional halfspaces.
result Near-optimal label complexity under Massart noise and lower than passive learning under Tsybakov noise.
Online active regression algorithms minimize label queries for efficient data regression.
problem Efficiently predict data points with minimal label queries in an online setting.
method Proposed online algorithms for active regression under ℓ_p loss, achieving (1+ε)-approximation with minimal label queries.
result Achieves (1+ε)-approximation with only ε^(-1) d log(nκ) label queries, matching offline methods in performance.
Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an agent in a constrained environment to concurrently reason about both its internal …
Spectral gradient methods outperform Euclidean in certain deep learning scenarios.
problem When do spectral gradient updates outperform Euclidean in deep learning?
method Layerwise condition comparing squared nuclear-to-Frobenius ratio to stable rank of activations.
result Spectral updates can be more effective than Euclidean in deep networks and transformers.
An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well. Previous theoretical work has rigorously characterized label complexity of activ…
Gradient descent with logistic loss can interpolate deep networks with smoothed ReLU activations under certain conditions.
problem Conditions for gradient descent to drive logistic loss to zero in deep networks with smoothed ReLU activations.
method Gradient descent applied to fixed-width deep networks with smoothed ReLU approximations (e.g., Swish, Huberized ReLU).
result Gradient descent can drive logistic loss to zero under specific conditions, providing bounds on convergence rate.
Screening rules help identify active sets in optimization problems.
problem Identifying active sets in optimization problems.
method Screening rules based on subdifferential sets and optimality conditions.
result The number of iterations needed depends only on the convergence rate.
Researchers infer gene activity in dividing cells, accounting for protein inheritance and division history.
problem Inferring protein production kinetics in dividing cells due to protein inheritance and division history.
method Adapted conditional normalizing flows to approximate intractable likelihoods from simulated data.
result Glc3 gene is mostly inactive under stress, with brief and transient expression.
Sufficient physical activity and restful sleep play a major role in the prevention and cure of many chronic conditions. Being able to proactively screen and monitor such chronic conditions would be a big step forward for overall health. The rapid increase in the popularity of wearable devices provides a significant new…
Generative AI predicts economic activity from corporate transcripts.
problem Predicting economic activity using existing measures like surveys.
method Extracted managerial expectations from transcripts using generative AI.
result AI Economy Score predicts economic activity up to 10 quarters ahead.
GAPA method provides efficient uncertainty quantification for pretrained networks.
problem Reliable uncertainty estimates for pretrained models are challenging.
method Post-hoc Gaussian Process Activations (GAPA) method that shifts Bayesian modeling from weights to activations.
result GAPA method provides efficient uncertainty quantification without altering the backbone's predictions.
This paper studies graphical model selection, i.e., the problem of estimating a graph of statistical relationships among a collection of random variables. Conventional graphical model selection algorithms are passive, i.e., they require all the measurements to have been collected before processing begins. We propose an…
Establishes upper bounds on generalization error in active learning.
problem Improving query algorithms in active learning.
method Derives upper bounds on generalization error using informativeness and representativeness query strategies.
result Validates the use of regularization techniques to ensure bounds' validity.
Study on critical points in random neural networks, revealing three regimes based on activation function.
problem Investigating the expected number of critical points in random neural networks.
method Deriving asymptotic formulas for critical points under infinite-width limit and suitable regularity conditions.
result Three distinct regimes of critical points behavior depending on activation function.
New active learning algorithm adapts to data without strict assumptions.
problem Efficiently label data with expensive labeling costs.
method Nonparametric adaptive active learning under local smoothness condition.
result Achieves minimax rate of convergence, performs almost as well as best non-adaptive algorithms.
New method uses trainable activations to make BNNs behave like GPs.
problem Making Bayesian Neural Networks (BNNs) behave like Gaussian Processes (GPs).
method Introduced trainable activations and periodic activations to map GP priors to BNNs. Used 2-Wasserstein distance for optimization.
result Method consistently outperforms existing approaches or matches heuristic methods.
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.
Complex-valued neural networks avoid spurious local minima.
problem Finding spurious local minima in neural networks.
method Proved no spurious local minima for shallow complex neural networks with quadratic activations.
result Complex-valued weights eliminate spurious local minima in neural networks.
Training feedforward neural networks with standard logistic activations is considered difficult because of the intrinsic properties of these sigmoidal functions. This work aims at showing that these networks can be trained to achieve generalization performance comparable to those based on hyperbolic tangent activations…
Paper provides label complexity guarantees for deep active learning.
problem Lack of rigorous label complexity guarantees for deep active learning.
method Studied deep active learning from nonparametric classification perspective.
result Proved near-optimal label complexity guarantees for deep active learning.
Deep Convolutional Sparse Coding (D-CSC) is a framework reminiscent of deep convolutional neural networks (DCNNs), but by omitting the learning of the dictionaries one can more transparently analyse the role of the activation function and its ability to recover activation paths through the layers. Papyan, Romano, and E…
Study efficient interactive learning for structured outputs with reliable computation.
problem Interactive learning with noisy labels and structured output spaces.
method Identify and utilize CRISPs (probabilistic models) that guarantee reliable and efficient computation of probabilistic quantities.
result CRISPs enable robust and efficient active and skeptical learning in large structured output spaces.
We present a simple noise-robust margin-based active learning algorithm to find homogeneous (passing the origin) linear separators and analyze its error convergence when labels are corrupted by noise. We show that when the imposed noise satisfies the Tsybakov low noise condition (Mammen, Tsybakov, and others 1999; Tsyb…
Counterfactual learning from observational data involves learning a classifier on an entire population based on data that is observed conditioned on a selection policy. This work considers this problem in an active setting, where the learner additionally has access to unlabeled examples and can choose to get a subset o…
SAMBA improves safe reinforcement learning with active exploration metrics.
problem Safe reinforcement learning in dynamic systems.
method Combines probabilistic modelling, information theory, and statistics. Uses novel metrics for out-of-sample Gaussian process evaluation.
result Orders of magnitude reduction in samples and violations compared to state-of-the-art methods.
Client adaptation improves federated learning performance with non-IID data.
problem Improving model performance in federated learning with non-identically and non-independently distributed data.
method Simulates heterogeneous clients to learn client-specific conditioning using a conditional gated activation unit.
result Client adaptation enhances model performance across balanced and imbalanced data sets from audio and image domains.
We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly nat…
We develop a primal dual active set with continuation algorithm for solving the \ell^0-regularized least-squares problem that frequently arises in compressed sensing. The algorithm couples the the primal dual active set method with a continuation strategy on the regularization parameter. At each inner iteration, it fir…
New insights into neural network training efficiency.
problem Understanding the optimal initialization for deep neural networks.
method Exploring the edge of chaos and saturation of tanh activation function.
result The line of uniformity in phase space intersects the edge of chaos, indicating saturation begins to hinder training efficiency.
DiAL uses Bayesian Dirichlet random fields for active learning with sparse labels.
problem Active learning with limited labeled data.
method Bayesian Dirichlet random field for feature-conditional class probabilities, calibrating with graph Laplacian.
result Competitive performance in low-label rate graph learning tasks.
Parallelizes active learning for Bayesian inference using Nested Sampler.
problem Expensive likelihood evaluations in complex experiments.
method Uses Nested Sampler to generate nearly-optimal batches of candidates in parallel.
result Comparable accuracy to sequential conditioning with efficient parallelization.
Deep neural networks can interpolate any dataset in the overparametrized regime.
problem Interpolating any dataset with deep neural networks in the overparametrized regime.
method Proving universal approximations and interpolating any dataset with deep neural networks, considering specific conditions on activation functions.
result Interpolation of any dataset is possible in the overparametrized regime with deep neural networks.
New active learning framework for multiclass classification beyond realizability assumption.
problem Active learning in non-realizable settings with convex model classes.
method Surrogate risk minimization, epoch-based fitting, aggregation of models.
result Achieves label and sample complexity comparable to prior work in non-realizable settings.