Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

81161242322 · Jun 202019922001200920172026
48 results for activation manifold

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.

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…

2004-12-20abs ↗pdf ↗

New framework tackles high-dimensional reliability analysis using surrogate models and active subspaces.

problem High computational cost and curse of dimensionality in reliability analysis of high-dimensional systems.
method Sparse Active Subspace (SAS) algorithm for identifying low-dimensional manifolds and constructing efficient surrogate models.
result Proposed framework significantly improves accuracy and efficiency of reliability analysis compared to existing methods.

We present an approach to analyze C1(Rm)C^1(\mathbb{R}^m) functions that addresses limitations present in the Active Subspaces (AS) method of Constantine et al.(2015; 2014). Under appropriate hypotheses, our Active Manifolds (AM) method identifies a 1-D curve in the domain (the active manifold) on which nearly all values o…

2019-04-30abs ↗pdf ↗

LASER compresses recursive model activations by exploiting their low-dimensional structure.

problem Understanding and optimizing the geometric structure of recursive reasoning trajectories.
method Dynamic low-rank basis tracking via matrix-free subspace tracking with a fidelity-triggered reset mechanism.
result Recursive activations occupy a linear, low-dimensional subspace that can be compressed efficiently.

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.

Study shows how correlations between neural activity affect classification capacity.

problem Understanding how correlations between neural activity impact classification performance.
method Calculated the capacity of neural activity on spherical manifolds with and without correlations between centroids and axes.
result Introducing correlations between neural activity centroids pushes spheres closer together, while correlations between axes shrink their radii, revealing a duality between correlations and geometry in classification.

New insights into data geometry reveal manifold structure in grid-cell activity.

problem Understanding the roles of different dimensions in data geometry.
method Generalised Hanson-Wright inequality and random function model analysis.
result Persistence diagrams reveal latent homology and manifold structure.

In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding space between the visual and textual manifolds. On the visual side, we used activity videos and a state-of-the-art 3D convolutional action recog…

2020-01-22abs ↗pdf ↗

SAEs struggle with curved activation manifolds, revealing layer-dependent scaling laws.

problem Sparse autoencoders' reconstruction error varies across layers, not fitting existing scaling laws.
method Cross-layer study of 844 SAE checkpoints, fitting and regressing on manifold geometry.
result Manifold geometry predicts layer-dependent width exponents in SAEs, with transferable coefficients.

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.

GPMI method interpolates uncertain atrial conduction velocity on non-Euclidean manifolds.

problem Uncertainty in atrial conduction velocity calculations.
method Gaussian Process Manifold Interpolation (GPMI) on human atrial manifolds.
result GPMI accounts for atrial topology and calculates CV uncertainty.

REMAL: Residual Equilibrium Manifold Active Learning for Surrogate-Based Multidisciplinary Design Analysis

problem Multidisciplinary design analysis of coupled engineering systems requires solving equilibrium states where all disciplinary coupling variables are consistent.
method Residual manifold surrogate modeling framework for coupled systems.
result REMAL learns a surrogate model of the joint residual manifold via multitask Gaussian process models.

Active learning selects high-quality examples for text-to-SQL systems.

problem Efficiently annotate large language models for text-to-SQL systems.
method Formalizes example selection as a constrained experimental design problem over semantic query embeddings, proposing a stratified greedy algorithm that maximizes heteroscedastic mutual information.
result Proposed method significantly reduces labeling effort while maintaining high text-to-SQL retrieval accuracy.

Enhances Gaussian process regression with multi-fidelity models and active subspaces for high-dimensional problems.

problem Data scarcity and high-dimensional input spaces with low intrinsic dimensionality.
method Employ Gaussian processes in a Bayesian setting, augmenting with low-fidelity models, and exploiting active subspaces.
result Improves model accuracy through multi-fidelity Gaussian process regression with active subspaces.

Improved neural population modeling using shared features and ensemble detection.

problem Missing shared coding properties in neural latent variable models.
method Feature sharing across tuning curves and soft clustering of neurons.
result More interpretable and better-performing neural population models.

We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function…

2018-02-01abs ↗pdf ↗

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.

Scientists and engineers rely on accurate mathematical models to quantify the objects of their studies, which are often high-dimensional. Unfortunately, high-dimensional models are inherently difficult, i.e. when observations are sparse or expensive to determine. One way to address this problem is to approximate the or…

2018-02-07abs ↗pdf ↗

Latent FxLMS accelerates ANC by adapting along low-dimensional filter weights.

problem Improving active noise control with neural adaptive filters.
method Training an auto-encoder on filter coefficients, constraining weights to latent variables, and updating in latent space.
result Latent FxLMS converges in fewer steps with comparable error to standard FxLMS.

This paper proposes a geometry-aware active learning framework for spatiotemporal dynamic systems.

problem Challenges in modeling complex dynamic systems with 3D geometries and time evolution.
method Geometry-aware spatiotemporal Gaussian Process (G-ST-GP) and adaptive active learning strategy.
result The proposed framework outperforms traditional methods in predicting high-dimensional dynamic behaviors.

New neural network with RePU activation approximates smooth functions and their derivatives.

problem Approximating smooth functions and their derivatives with neural networks.
method Differentiable neural networks with RePU activation functions.
result Improved approximation error bounds for RePU-activated neural networks.

Theory of MoE Transformers' generalization and scaling.

problem Understanding the generalization and scaling of Mixture-of-Experts (MoE) Transformers.
method Developed a theory that separates active capacity from routing combinatorics, derived a sup-norm covering-number bound, and proved a constructive approximation theorem.
result Generalization and scaling laws for MoE Transformers, showing how active capacity and routing structure affect performance.

Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an "activation ensemble" because it allows the use of multiple activation functio…

2017-02-24abs ↗pdf ↗

This paper studies activation sparsity in large language models, finding key trends and implications.

problem Activation sparsity in large language models (LLMs) can be improved for efficiency and interpretability.
method Proposes PPL-p%p\% sparsity, analyzes trends with training data, width-depth ratio, and parameter scale.
result ReLU is more efficient for sparsity than SiLU, and deeper architectures can improve sparsity.

It has been empirically observed that the flatness of minima obtained from training deep networks seems to correlate with better generalization. However, for deep networks with positively homogeneous activations, most measures of sharpness/flatness are not invariant to rescaling of the network parameters, corresponding…

2019-02-06abs ↗pdf ↗

First the title could be also understood as ``3-manifolds related by non-zero degree maps" or "Degrees of maps between 3-manifolds" for some aspects in this survey talk. The topology of surfaces was completely understood at the end of 19th century, but maps between surfaces kept to be an active topic in the 20th centur…

2003-04-21abs ↗pdf ↗

Deep networks can adapt to intrinsic dimensionality beyond domain constraints.

problem Approximating functions on low-dimensional manifolds with high-dimensional data.
method Two-layer compositions with ReLU activation, using dimensionality reducing feature maps.
result Near optimal approximation rates depend on the complexity of the dimensionality reducing map, not the ambient dimension.

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the activation, and the weights capture the scale. Here we propose to train the netw…

2019-01-28abs ↗pdf ↗

Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples giv…

2012-07-11abs ↗pdf ↗

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.

RAN model recognizes multiple activities from unlabeled sensor data.

problem Handling weakly labeled multi-activity data from wearable sensors.
method Recurrent Attention Networks (RAN) for sequential multi-activity recognition and localization.
result RAN model can infer multiple activities and determine activity locations from unlabeled data.

Active testing reduces label costs for efficient model evaluation.

problem Real-world applications require expensive test labels, disconnecting from existing model evaluation methods.
method Derives acquisition strategies to select test points efficiently, addressing label bias and variance.
result Active testing improves model evaluation efficiency without sacrificing accuracy.

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…

2020-02-17abs ↗pdf ↗

Survey of trainable activation functions in neural networks.

problem Improving neural network performance through trainable activation functions.
method Taxonomy and comparison of recent and past models of trainable activation functions.
result Many trainable activation functions are equivalent to adding neuron layers with fixed activation functions and simple constraints.

This paper analyzes and improves active learning techniques for real-world projects.

problem Reducing labelling effort in machine learning models with real-world constraints.
method Systematic study of active learning issues, proposing techniques to address model convergence, annotation error, and dataset imbalance.
result Presentation of two techniques to speed up active learning: partial uncertainty sampling and larger query size.