A model studies deep neural networks with binary synapses under connection removal.
problem Understanding the mechanism of deep learning from a theoretical perspective.
method Random active path model with diluted binary synapses under removal perturbation.
result A critical value of perturbation separates spin glass and paramagnetic phases, with the latter having poor generalization performance.
The paper analyzes the role of ReLU gates in deep learning networks.
problem Understanding the role of gates in deep learning networks.
method Developed neural path features (NPF) and neural path values (NPV) to characterize the active sub-networks during training.
result The neural path kernel associated with NPFs is a fundamental quantity that characterizes the information stored in the gates of a DNN.
Study on function sensitivity in random DNNs using large deviation theory.
problem Understanding function sensitivity in finite-size deep neural networks.
method Large deviation theory and path integral analysis applied to random DNNs with ReLU and sign activations.
result Random DNNs with ReLU activations are more robust to parameter perturbations.
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.
Gated Path Planning Network improves path planning efficiency and stability.
problem Training instability and optimization issues in Value Iteration Networks.
method Reframed VINs as recurrent-convolutional networks with gated update equations.
result Gated Path Planning Network outperforms VINs in various metrics.
Paper develops SINNOs for approximating stochastic processes.
problem Approximating stochastic processes with neural networks.
method Developed stochastic interpolation neural network operators (SINNOs) with random coefficients.
result Established boundedness, interpolation accuracy, and approximation capabilities of SINNOs.
Characterizes neural kernel and NNGP for various activations.
problem Understanding neural kernels and NNGP for non-RELU activations.
method Characterization of RKHS for various activation functions.
result Broad class of non-infinitely smooth activations generate equivalent RKHSs at different depths.
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.
The study examines price formation in complex networks and finds efficiency varies by network structure.
problem Understanding price formation and efficiency in complex networks.
method Price formation experiments with human subjects in large networks, agent-based model construction.
result Prices are higher and trade less efficient in small-world networks compared to random networks.
Model place cells as spatial embeddings for efficient path planning and cognitive map construction.
problem Encoding spatial navigation in the hippocampus.
method Model place cells using spectral decomposition of multi-step random walk transition kernels, inducing sparsity and adjacency.
result Place cells encode spatial information through non-negativity and inner-product structure, forming a cognitive map.
New approach treats neural networks with piecewise linear activations using tropical geometry.
problem Upper bounds on linear regions of neural networks with ReLU or leaky ReLU activations.
method Treat neural network layers with piecewise linear activations as tropical polynomials, refining upper bounds using tropical geometry.
result Upper bounds on linear regions improved to $\min\left\{ 2^m, \sum_{j=0}^n \binom{m}{j}
ight\}$, where n,m are the number of inputs and outputs, respectively. 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.
New modifiers improve noisy RNN replay in hippocampal networks.
problem Improving noisy RNN replay in hippocampal networks.
method Three approaches: hidden state leakage, adaptation, and momentum.
result Hidden state leakage, adaptation, and momentum improve noisy RNN replay.
Optimizes exploration in networks by interpolating between random and deterministic paths.
problem Balancing exploitation and exploration in network routing with constraints.
method Developed a constrained randomized shortest-paths framework using Lagrangian duality and iterative procedures.
result Optimal routing policy that interpolates between random and deterministic paths while satisfying constraints.
A new slicing method speeds up sliced Wasserstein estimation.
problem Efficiently estimating sliced Wasserstein distance.
method Random-Path Projecting Direction (RPD) for fast sampling.
result RPSW and IWRPSW show favorable performance in training generative models.
Deep networks with path norm regularization can approximate analytic functions.
problem Approximating analytic functions with neural networks.
method Path norm regularized deep networks with activation function.
result Deep networks can approximate analytic functions with logarithmic dependence on approximation error.
Develops path integral for spiked tensor model dynamics.
problem Dynamics of spiked tensor model with random initial conditions.
method Path integral approach applied to partial differential equations.
result Large-N saddle point equations dominated by melonic diagrams. PAN improves graph neural networks using path integrals.
problem Efficiency and performance of graph neural networks.
method PAN uses path integrals to generalize graph Laplacian, incorporating all paths between nodes.
result PAN achieves state-of-the-art performance on benchmark tasks.
A new method for embedding heterogeneous networks using spacey random walks.
problem Stationarity issues in meta-path guided random walks for HIN embedding.
method Heterogeneous personalized spacey random walk.
result Substantial improvement over existing network embedding algorithms.
We study pathwise invariances of centred random fields that can be controlled through the covariance. A result involving composition operators is obtained in second-order settings, and we show that various path properties including additivity boil down to invariances of the covariance kernel. These results are extended…
Landmark-based node embeddings approximate shortest path distances in random graphs.
problem Capturing global graph distances in node representations.
method Landmark-based node embeddings using shortest path distances from a subset of reference nodes (landmarks).
result Random graphs require lower dimensions in landmark-based embeddings compared to worst-case graphs.
Framework combines random features with CDEs for efficient time-series learning.
problem Efficient training of time-series models with strong inductive bias.
method Random Fourier CDEs and Random Rough DEs using continuous-time reservoirs and log-ODE discretization.
result Unified perspective on random-feature reservoirs and path-signature theory.
Path regularization improves GFlowNets exploration and generalization.
problem Improving GFlowNets exploration and generalization.
method Path regularization based on optimal transport theory.
result Path regularization enhances GFlowNets to generate more diverse and novel candidates.
Global approximation for piecewise linear paths via signatures.
problem Global approximation theorems for piecewise linear paths.
method Using signatures of piecewise linear paths and their density in Lp-norms. result Linear functionals of signatures are dense in Lp-norms under an integrability condition. New graph distances derived from optimal transport framework using path flows.
problem Develop new graph distances for clustering and classification.
method Bag-of-paths framework with Gibbs-Boltzmann distribution and optimal transport relaxation.
result Interpolates between shortest-path and resistance distances, improving performance.
Active covariance estimation using random sub-sampling of variable subsets.
problem Estimating covariance matrices for partially observed random vectors.
method Unbiased covariance estimator under a model of partially observed variables and active learning framework.
result Derivation of error bounds revealing relations between sub-sampling probabilities and covariance matrix entries.
Proposes ANN for more accurate path loss prediction in urban environments.
problem Inaccurate path loss prediction in complex urban environments.
method Artificial Neural Network (ANN) for multi-dimensional regression modeling of path loss.
result The proposed ANN model is more accurate and flexible than conventional linear models.
Proposes a new method for generating random parameters in neural networks.
problem Improving randomized learning of feedforward neural networks.
method Randomly selects slope angles, rotates activation functions, and distributes them across the input space.
result The method gives better results than the common approach, especially for complex target functions.
This research improves DNN defense by profiling and analyzing effective paths.
problem Defending against adversarial attacks on deep neural networks.
method Profiling DNN models into functional blocks and aggregating per-image effective paths to class-level effective paths.
result Adversarial images activate different effective paths from normal images.
C-RSP embeds multi-view graphs using randomized shortest paths.
problem Combining multiple views of a graph to improve inference quality.
method C-RSP algorithm that generates a common embedding using RSP.
result C-RSP outperforms benchmarks in embedding and clustering tasks.
The paper proposes a method to improve random forest classification accuracy by weighting trees based on their decision path reliability.
problem Random forests' uniform voting fails to correct errors in regions where incorrect tree representations outnumber correct ones.
method The paper introduces using the structural pattern of each tree's decision path as an instance-adaptive reliability signal to identify and weight more reliable trees.
result Using the proposed method yields a statistically significant accuracy improvement over RF on 36 binary classification benchmarks.
We give a proof of the sublinear tracking property for sample paths of random walks on various groups acting on spaces with hyperbolic-like properties. As an application, we prove sublinear tracking in Teichmueller distance for random walks on mapping class groups, and on Cayley graphs of a large class of finitely gene…
Active learning reduces simulation needs for high-fidelity mobility maps.
problem Efficiently training machine learning classifiers for high-fidelity mobility maps.
method Active learning based on PAC learning theory to reduce simulation needs.
result Our sampling algorithm trains neural networks with higher accuracy using less than half the number of simulations.
Partial covariance factorizes in path diagrams, simplifying analysis.
problem Understanding partial covariance in complex diagrams.
method Factorization of partial covariance over nodes and edges.
result Simpson's paradox cannot occur in singly-connected diagrams.
Study shows sample noise impacts active learning performance.
problem Impact of sample noise on active learning performance.
method Proposed Incremental Weighted K-Means for noisy samples.
result Robust sampler improves synthetic tasks but only marginally in real-life.
A new type of random forest improves robustness against noisy data.
problem Noise in test samples damages random forest performance.
method Introduces denoising autoencoders into random forests to identify and correct incorrect decisions.
result Improves estimation accuracy by considering multiple traversal paths for incorrect nodes.
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.
Researchers add random metrics to data models to enable operations.
problem Lack of meaningful operations in learned low-dimensional representations.
method Endow latent space of generative models with a random Riemannian metric.
result Derived tight error bounds on expected distances in deterministic approximations.
Improves neural network performance by normalizing activation functions.
problem Improving convergence speed and robustness of neural networks.
method Transforming existing activation functions into ones with better properties.
result Significantly promotes convergence robustness, maximum training depth, and anytime performance.
There have lately been several suggestions for parametrized distances on a graph that generalize the shortest path distance and the commute time or resistance distance. The need for developing such distances has risen from the observation that the above-mentioned common distances in many situations fail to take into ac…
Study models market volatility with persistent and temporary impacts.
problem Microstructure of rough volatility models driven by Poisson measures.
method Existence and uniqueness of solutions for stochastic path-dependent Volterra equations.
result Volatility process converges to fractional Heston model with spikes.
We investigate the extension of the multilevel Monte Carlo path simulation method to jump-diffusion SDEs. We consider models with finite rate activity, using a jump-adapted discretisation in which the jump times are computed and added to the standard uniform dis- cretisation times. The key component in multilevel analy…
We develop a method to describe laws of random surfaces using surface holonomy.
problem Describing laws of random surfaces with structure.
method Introduce surface holonomy and develop expected surface developments.
result Expected surface development provides a structured description of random surface laws.
We provide a general construction of time-consistent sublinear expectations on the space of continuous paths. It yields the existence of the conditional G-expectation of a Borel-measurable (rather than quasi-continuous) random variable, a generalization of the random G-expectation, and an optional sampling theorem that…
EntroPath learns manifold geometry from diffusion paths.
problem Learning geodesic geometry from data graphs with spurious shortcuts.
method Maximum Entropy Path Ensemble Embedding (MERW) with k-step diffusion paths.
result EntroPath converges to squared geodesic distance in the short-time limit.
We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the sense that they rely on estimates of expectations of functions of filtered random e…
Representations based on random walks can exploit discrete data distributions for clustering and classification. We extend such representations from discrete to continuous distributions. Transition probabilities are now calculated using a diffusion equation with a diffusion coefficient that inversely depends on the dat…
Diagonal linear networks converge to lasso regularization path during training.
problem Understanding the regularization behavior of diagonal linear networks.
method Analyzing the training trajectory of diagonal linear networks and comparing it to the lasso regularization path.
result The training trajectory of diagonal linear networks is closely related to the lasso regularization path.