Study embeddings between Barron spaces with various activation functions, focusing on RePU.
problem Understanding the influence of activation functions on infinitely wide neural networks.
method Prove embeddings by constructing push-forward maps on measures representing functions.
result Barron spaces with RePU activation have a hierarchical structure similar to Sobolev spaces.
Active learning selects inputs for GPSSM to learn latent states.
problem Optimally learn latent states of a GPSSM through active selection of inputs.
method Use mutual information to select informative inputs; approximate mutual information for GPSSM.
result Effective active learning of GPSSM dynamics in physical systems.
Develops active intervals for geodesics in Teichmüller space.
problem Understanding geodesics in Teichmüller space with no backtracking.
method Defines active intervals for subsurfaces along geodesics in Thurston metric.
result Active intervals represent reparametrized quasi-geodesics in curve graphs with bounded movement outside.
Extends active subspace analysis to infinite dimensions.
problem Dimension reduction in infinite dimensional functionals.
method Defines an operator for Hilbert space, extends Euclidean properties, proposes Monte Carlo procedure.
result Desirable properties extend to infinite dimensional setting.
Hi-fi priors enhance BNNs by learning flexible activations.
problem Challenging to impose function-space priors on BNNs.
method Optimization techniques to learn flexible activations.
result BNNs with flexible activations can achieve desired priors.
Active sampling improves design space exploration for analog circuits.
problem Efficiently exploring the space of design features in analog circuits with many parameters.
method Combining drastic dimension reduction with sensitivity analysis and Bayesian surrogate modeling for active sampling.
result The proposed active sampling flow outperforms traditional Monte-Carlo sampling.
The paper shows neural networks can approximate functions over non-compact domains with non-polynomial activation.
problem Approximating functions over non-compact domains using neural networks.
method Using single-hidden-layer feedforward neural networks with non-polynomial activation functions over non-compact subsets of Euclidean spaces.
result Neural networks can approximate functions in weighted Ck-spaces and weighted Sobolev spaces over unbounded domains. 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.
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.
The representations learned by deep neural networks are difficult to interpret in part due to their large parameter space and the complexities introduced by their multi-layer structure. We introduce a method for computing persistent homology over the graphical activation structure of neural networks, which provides acc…
In this paper, we investigate the geometric structure of activation spaces of fully connected layers in neural networks and then show applications of this study. We propose an efficient approximation algorithm to characterize the convex hull of massive points in high dimensional space. Based on this new algorithm, four…
Proves existence of optimal shallow neural networks with ReLU activation.
problem Proving the existence of optimal shallow feedforward networks with ReLU activation.
method Proves existence of global minima in the loss landscape for continuous target functions using shallow feedforward neural networks with ReLU activation.
result Existence of global minima in the loss landscape for shallow feedforward networks with ReLU activation.
Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we use recent advances in deep learning to learn the state space an…
Active learning selects optimal measurement times for inferring continuous paths from sparse data.
problem Inferring continuous probability paths from sparse snapshots in high-fidelity domains like single-cell biology.
method Extends active experimentation to the space of measures using Linearized Optimal Transport (LOT) for probabilistic surrogate modeling.
result Empirical results show that the proposed strategy outperforms uncertainty-agnostic baselines.
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.
Active learning improves GP regression on complex, high-dimensional data.
problem Improving Gaussian Process regression in high-dimensional spaces with discontinuous functions.
method Combines manifold learning with active learning to optimize data selection and reduce dimensionality.
result Superior performance over random learning in synthetic data experiments.
Regularization and normalization have become indispensable components in training deep neural networks, resulting in faster training and improved generalization performance. We propose the projected error function regularization loss (PER) that encourages activations to follow the standard normal distribution. PER rand…
New method reduces version space for CNNs, improving active learning performance.
problem Sampling bias in active learning hinders optimal hypothesis finding in neural networks.
method Version space reduction through prior mass reduction and diameter reduction, proposing a new Gibbs-vote disagreement method.
result Diameter-based querying method reduces version space more effectively than prior mass reduction and other methods.
In this paper we study a symmetry group of vector space. Basis manifold is a homogeneous space of a symmetry group. This concept leads us to the definition of active and passive transformations on basis manifold. Active transformation can be expressed as a transformation of vector space. Passive transformation gives ab…
In this paper we address the problem of pool based active learning, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothesis in a given hypothesis space. For the space of linear classifiers and the squared loss we show that UPAL is equivalent to an exponentially…
Improves active learning efficiency by warping input space based on observed outputs.
problem Insensitivity of Gaussian process uncertainty to actual observations.
method Input warping with learned monotone reparameterization to adjust acquisition function behavior.
result Significantly improved sample efficiency across various benchmarks, especially in non-stationary conditions.
Smooth activations enable optimal error rates in neural networks for Sobolev function classes.
problem Achieving optimal approximation and estimation error rates for neural networks in Sobolev function classes.
method Study of neural networks with smooth activations, proving optimal rates via approximation and statistical properties.
result Constant-depth networks with smooth activations achieve optimal rates of approximation and estimation, demonstrating smoothness adaptivity.
Study on neural networks' storage capacity and solution space structure.
problem Understanding the storage capacity and solution space structure of neural networks.
method Replica method from statistical physics.
result Storage capacity per parameter remains finite even with infinite width and weights exhibit negative correlations.
The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most commonly-used in practice. This paper shows that evolutionary algorithms can discover novel…
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. U…
Sharp bounds on neural network approximation rates and widths.
problem Estimating approximation rates, metric entropy, and n-widths of shallow neural networks.
method Introducing smoothly parameterized dictionaries and providing upper and lower bounds.
result Sharp bounds on approximation rates, metric entropy, and n-widths for neural networks with various activation functions.
Periodic activation functions improve neural network reliability and interpretability.
problem Neural networks reinforce hidden biases, making them unreliable and hard to interpret.
method Introduce periodic activation functions in Bayesian neural networks to establish a connection with stationary Gaussian process priors.
result Periodic activation functions, including sinusoidal, triangular, and ReLU, improve model performance and sensitivity to perturbations.
A new method reduces high-dimensional parameter spaces for faster numerical tasks.
problem Efficiently reducing high-dimensional parameter spaces for numerical tasks.
method Local Active Subspaces (LAS) combining active subspaces with clustering techniques.
result Significant speed-up in numerical tasks through efficient dimension reduction.
Consider a set of latent factors whose observable effect of activation is caught on a measure space that appears as a grid of bits tacking value in {0,1}. This paper intend to deliver a theoretical and practical answer to the question: Given that we have access to a perfect indicator of the activation of latent f…
While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacting performance on th…
There is a large body of work on convergence rates either in passive or active learning. Here we first outline some of the main results that have been obtained, more specifically in a nonparametric setting under assumptions about the smoothness of the regression function (or the boundary between classes) and the margin…
Neural networks cannot approximate certain functions in Sobolev spaces, leading to unbounded parameter growth.
problem Non-closedness of sets of neural networks in Sobolev spaces.
method Construction of sequences of neural networks whose realizations converge to functions not realizable by neural networks.
result Sets of realized neural networks are not closed in order-(m−1) Sobolev spaces Wm−1,p for p∈[1,∞]. Fink AGN classifier achieves high accuracy in classifying active galactic nuclei.
problem Classifying active galactic nuclei from astronomical data.
method Built features from photometric points and color estimation. Used active learning for optimized training sample. Applied traditional machine learning algorithms.
result Achieved 98.0% accuracy in classifying real alerts from ZTF.
Incremental methods for structure learning of pairwise Markov random fields (MRFs), such as grafting, improve scalability by avoiding inference over the entire feature space in each optimization step. Instead, inference is performed over an incrementally grown active set of features. In this paper, we address key compu…
Complexity measures for neural nets with general activations using path-based norms.
problem Control complexity of neural networks with arbitrary activation functions.
method Approximate general activations with ReLU networks and derive path-based norms for complexity control.
result Preliminary analyses of function spaces and regularized estimators.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
problem Understanding latent concept encodings in AI models.
method Probabilistic perspective on CAVs, deriving mean and covariance.
result CAVs can be adversarially manipulated, highlighting a vulnerability.
We extend neural networks with fractional and mixed activation functions for better function approximation.
problem Limitations in approximating higher-order smooth functions in complex spaces.
method Incorporating fractional exponents in activation functions and defining new density functions.
result Improved accuracy and broader applicability of neural network approximation theory.
We introduce a new and improved characterization of the label complexity of disagreement-based active learning, in which the leading quantity is the version space compression set size. This quantity is defined as the size of the smallest subset of the training data that induces the same version space. We show various a…
WiGS improves active learning for regression by dynamically selecting informative samples.
problem Reducing labeling costs in regression tasks.
method Formulated as a reinforcement learning problem, WiGS adapts the exploration-investigation balance.
result WiGS outperforms static methods in accuracy and labeling efficiency, especially in irregular data density.
We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, both phases actively requesting labels. We prove theoretical guarantees for both the generalization error and the label complexity of our al…
This paper proposes an improved active learning method using classification trees.
problem Reducing the size of training sets while maintaining high accuracy in supervised learning.
method A wrapper active learning method using a classification tree to sub-sample from low-entropy regions.
result The proposed method constructs accurate classification models even with severely restricted labeled data.
Unified theory of deep neural networks with diverse activations.
problem Understanding the relationship between depth and complexity in deep neural networks.
method Developed a unified function space theory for deep networks with various activations.
result Unified theory provides meaningful complexity for deep networks with diverse activations.
An activation boundary for a neuron refers to a separating hyperplane that determines whether the neuron is activated or deactivated. It has been long considered in neural networks that the activations of neurons, rather than their exact output values, play the most important role in forming classification friendly par…
There is a large body of work on convergence rates either in passive or active learning. Here we outline some of the results that have been obtained, more specifically in a nonparametric setting under assumptions about the smoothness and the margin noise. We also discuss the relative merits of these underlying assumpti…
A new framework scales active search for large datasets.
problem Scaling active search for large, high-dimensional data sets.
method Hierarchical Batch Bandit Search (HBBS) framework.
result HBBS improves performance and scalability for batch search.
The paper proves deep neural networks with analytic activation can approximate any function.
problem Approximating functions with neural networks using analytic activation functions.
method Elementary proofs for real and complex networks, Stone-Weierstrass theorem, Mergelyan's theorem.
result Closure of neural network classes equals space of polynomials for analytic activation.
A problem of considerable importance within the field of uncertainty quantification (UQ) is the development of efficient methods for the construction of accurate surrogate models. Such efforts are particularly important to applications constrained by high-dimensional uncertain parameter spaces. The difficulty of accura…
Unified Bayesian model explains in-context learning and activation steering in LLMs.
problem Understanding and controlling the behavior of large language models (LLMs) through prompts and activations.
method Developed a Bayesian model to explain and predict the effects of in-context learning and activation steering.
result Unified model predicts distinct phases and sudden shifts in LLM behavior, explaining prior empirical phenomena.