Active learning method estimates nonlinear systems efficiently.
problem Identifying nonlinear dynamical systems with continuous states and actions.
method Repeating three steps: trajectory planning, tracking, and re-estimation.
result Estimates nonlinear dynamical systems at a parametric rate.
Study shows how activation functions impact the storage capacity of treelike neural networks.
problem Understanding the role of activation functions in neural network expressive power.
method Analysis of treelike two-layer networks with various activation functions in the infinite-width limit.
result Activation functions affect storage capacity and robustness, with nonlinearity increasing capacity and decreasing robustness.
The paper studies how neural networks evolve representations, finding a unique fixed point for nonlinear activations.
problem Understanding how neural networks transform input data across layers.
method Theoretical framework for the evolution of the kernel sequence, using mean-field regime and Hermite polynomials.
result For nonlinear activations, the kernel sequence converges globally to a unique fixed point.
Token-adaptive FFN design improves LLM expressivity.
problem Fixed activation functions limit FFN expressivity in LLMs.
method Mixture of Activations (MoA) and learnable activations (LA).
result MoA achieves lower terminal loss and better scaling than baselines.
Graph neural networks (GNNs) have been shown to replicate convolutional neural networks' (CNNs) superior performance in many problems involving graphs. By replacing regular convolutions with linear shift-invariant graph filters (LSI-GFs), GNNs take into account the (irregular) structure of the graph and provide meaning…
New neural architectures with multivariate nonlinearities are optimal in function space.
problem Optimality of neural architectures with multivariate nonlinearities.
method Construction of Banach spaces via k-plane transform and sparsity-promoting norm, proving representer theorem. result Neural architectures with multivariate nonlinearities are optimal in function space.
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.
Theory explains deep nonlinear networks' plateaus and transitions.
problem Understanding long plateaus and feature acquisition transitions in deep nonlinear networks.
method Derived an exact identity for Frobenius norms, classified activation functions, and reduced matrix flow to a scalar ODE.
result Escape time law τ⋆=Θ(ε−(r−2)) for deep nonlinear networks, where r is the number of bottleneck layers. New algorithm tackles stochastic optimization with inequality constraints.
problem Stochastic optimization with inequality constraints in various applications.
method Active-set stochastic sequential quadratic programming (StoSQP) with a differentiable exact augmented Lagrangian.
result Global convergence for any initialization, KKT residuals converge to zero almost surely.
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
problem Training neural networks to mimic the complex interactions of brain neurons.
method Developed a network-in-network architecture with two-input activation functions, optimized hyperparameters, and compared to conventional ReLU networks.
result Two-input activation functions can learn soft XOR functions, improving network performance and robustness.
Optimized nonlinearities enhance generalization in random feature models.
problem Improving generalization performance in random feature models.
method Analyzed and defined optimal nonlinearities from Gaussian model parameters.
result Optimized nonlinearities achieve better generalization performance than ReLU.
This paper explores adaptive neural activation in RNNs for better learning.
problem Fixed neural activation functions limit the performance and adaptability of RNNs.
method Developed a novel parametric family of nonlinear activation functions inspired by biological neurons.
result Adaptive neural activation improves learning speed and performance in RNNs.
Optical ESNs enable flexible, efficient machine learning with reduced energy.
problem Implementing universal computational capabilities in machine learning.
method Optical implementation of ESNs leveraging stimulated Brillouin scattering.
result Efficient, scalable, and memory-capable optical reservoir computing.
Safe active learning for time-series models with Gaussian processes.
problem Learning time-series models while respecting safety constraints.
method Employing Gaussian processes with a nonlinear exogenous input structure, the approach dynamically explores the input space to generate data for model learning.
result The approach effectively learns time-series models under safety constraints, as demonstrated in a technical application.
K-means is a classical clustering algorithm with wide applications. However, soft K-means, or fuzzy c-means at m=1, remains unsolved since 1981. To address this challenging open problem, we propose a novel clustering model, i.e. Probabilistic K-Means (PKM), which is also a nonlinear programming model constrained on lin…
Study shows attention-style models learn pairwise interactions efficiently.
problem Learning pairwise interactions in attention-style models.
method Proved minimax rate of convergence for learning pairwise interactions.
result Minimax rate is M−2β+12β independent of embedding dimension and token number. Study approximates nonlinear functionals using deep ReLU networks.
problem Approximating nonlinear continuous functionals with neural networks.
method Constructs continuous piecewise linear interpolation under simple triangulation, analyzes rates of approximation.
result Established rates of approximation for functional deep ReLU networks.
The paper investigates how activation functions impact the training of Neural ODEs, leading to global convergence.
problem Challenges in training Neural ODEs, particularly gradient computation accuracy and convergence analysis.
method Investigates the impact of activation functions on the training dynamics of Neural ODEs.
result Establishes global convergence of Neural ODEs under gradient descent in overparameterized regimes.
New method finds basins of attraction without needing system models.
problem Determining basins of attraction (BoA) for nonlinear systems without prior knowledge.
method Hybrid Active Learning (HAL) method combining AST, AL, and DBS.
result Efficiently finds and labels boundary of BoA without model knowledge.
In this paper, we have extended the well-established universal approximator theory to neural networks that use the unbounded ReLU activation function and a nonlinear softmax output layer. We have proved that a sufficiently large neural network using the ReLU activation function can approximate any function in L1 up …
We study discrete time dynamical systems governed by the state equation ht+1=φ(Aht+But). Here A,B are weight matrices, φ is an activation function, and ut is the input data. This relation is the backbone of recurrent neural networks (e.g. LSTMs) which have broad applications in sequential learning tasks. …
We develop a new DTSM with nonlinearities using Gaussian Processes for better interest rate forecasting.
problem Linear DTSMs fail to capture nonlinear relationships between macroeconomic variables and interest rates.
method We propose a Gaussian Process-based sequential Monte Carlo estimation and forecasting scheme.
result Nonlinear models outperform linear ones in forecasting core inflation, leading to significant economic value gains.
A new deep learning framework selects representative samples for unsupervised learning.
problem Selecting representative samples for unsupervised learning in non-linear data.
method DUAL framework using an encoder-decoder architecture to learn nonlinear embeddings and a selection block to choose representative samples.
result DUAL outperforms state-of-the-art methods in selecting representative samples for unsupervised learning.
We propose a model of fractal point process driven by the nonlinear stochastic differential equation. The model is adjusted to the empirical data of trading activity in financial markets. This reproduces the probability distribution function and power spectral density of trading activity observed in the stock markets. …
Rational neural networks approximate functions more efficiently with less depth.
problem Choosing optimal nonlinear activation functions in neural networks.
method Rational activation functions with optimal bounds and efficiency proofs.
result Rational neural networks approximate smooth functions more efficiently than ReLU networks with exponentially smaller depth.
Improved stability analysis of neural network systems using Zames-Falb multipliers.
problem Analyzing stability of linear systems with neural network nonlinearities.
method Using integral quadratic constraints, sector-bounded and slope-restricted structure, and acausal Zames-Falb multipliers.
result Flexible and versatile framework for stability analysis with improved computational efficiency.
Nonlinearity is crucial to the performance of a deep (neural) network (DN). To date there has been little progress understanding the menagerie of available nonlinearities, but recently progress has been made on understanding the rôle played by piecewise affine and convex nonlinearities like the ReLU and absolute value …
Recent seminal work at the intersection of deep neural networks practice and random matrix theory has linked the convergence speed and robustness of these networks with the combination of random weight initialization and nonlinear activation function in use. Building on those principles, we introduce a process to trans…
Many real-world data sets, especially in biology, are produced by complex nonlinear dynamical systems. In this paper, we focus on brain calcium imaging (CaI) of different organisms (zebrafish and rat), aiming to build a model of joint activation dynamics in large neuronal populations, including the whole brain of zebra…
Bayesian adaptive designs can be biased by active learning, especially with misspecified models.
problem Active learning bias in Bayesian adaptive experimental designs.
method Analysis of linear and preference learning models, empirical testing.
result Model misspecification and noise influence active learning bias in Bayesian designs.
NAST generalizes scattering transform for non-stationary time series analysis.
problem Analyzing non-stationary time series data.
method Neural activation of scattering transform with various activation functions and high pass filters.
result Central and non-central limit theorems for NAST of Gaussian processes.
Proposes a stratified sampling method for high-dimensional models using neural active manifolds.
problem Uncertainty propagation in computationally expensive models with many inputs.
method Neural active manifolds for nonlinear dimensionality reduction, followed by stratification in the reduced space.
result Effective variance reduction in high-dimensional models using stratified sampling.
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation functio…
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation functio…
Novel F2NARX model improves surrogate modeling for stochastic dynamical systems.
problem Challenges in constructing accurate and efficient surrogate models for stochastic dynamical systems.
method Function-on-Function Nonlinear AutoRegressive model with eXogenous inputs (F2NARX) combining PCA and Gaussian process regression.
result F2NARX outperforms state-of-the-art NARX models in efficiency and accuracy.
ESE-FN improves elderly activity recognition accuracy.
problem Recognizing individual actions and human-object interactions in elderly activities.
method Exploits multi-modal features from RGB videos and skeleton sequences using ESE attentions and a new Multi-modal Loss.
result ESE-FN achieves best accuracy on ETRI-Activity3D dataset.
Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, …
Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at the cost of significantly reduced accuracy. In this paper, we present a novel a…
A new method for reducing model complexity using neural active manifolds.
problem Uncertainty quantification in computationally expensive models.
method Autoencoders and surrogate models to discover a neural active manifold.
result Neural active manifolds reduce model variance in multifidelity sampling.
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.
In this paper, we prove that depth with nonlinearity creates no bad local minima in a type of arbitrarily deep ResNets with arbitrary nonlinear activation functions, in the sense that the values of all local minima are no worse than the global minimum value of corresponding classical machine-learning models, and are gu…
This work frames active inference through control as inference, offering robust control algorithms.
problem Active inference framework lacks practical sensorimotor control algorithms.
method Frame active inference through control as inference, presenting trajectory optimization as inference.
result AI may be framed as partially-observed CaI when the cost function is defined in observation states.
Research uses deep learning and copulas to predict multivariate survival data.
problem Handling right-censored and correlated multivariate survival data.
method Integrates deep learning, copula functions, and survival analysis. Uses copula-based activation functions to model nonlinear dependencies.
result Enhanced prediction accuracy for multivariate survival responses.
Bayesian method improves predictions in overparameterized nonlinear regression.
problem Understanding overparameterization in nonlinear regression models.
method Bayesian framework with adaptive prior considering data spectral structure.
result Posterior contraction established for generalized linear and single-neuron models, demonstrating prediction consistency.
Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks the weights and biases of hidden nodes determining the nonlinear feature mapping a…
Training examples are not all equally informative. Active learning strategies leverage this observation in order to massively reduce the number of examples that need to be labeled. We leverage the same observation to build a generic strategy for parallelizing learning algorithms. This strategy is effective because the …
This article proposes an active learning method for high dimensional data, based on intrinsic data geometries learned through diffusion processes on graphs. Diffusion distances are used to parametrize low-dimensional structures on the dataset, which allow for high-accuracy labelings of the dataset with only a small num…
We investigate the loss surface of neural networks. We prove that even for one-hidden-layer networks with "slightest" nonlinearity, the empirical risks have spurious local minima in most cases. Our results thus indicate that in general "no spurious local minima" is a property limited to deep linear networks, and insigh…