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.

168,695 papers · 148 categories

Trend · papers per month

3.1%6.2%9.4%12.5% · Nov 202519922001200920172026
48 results for activation stability

Study proposes a stopping criterion for active learning based on error stability.

problem Improving predictive performance in active learning by adaptively annotating samples.
method Proposes a stopping criterion based on error stability for Bayesian active learning.
result Demonstrates the proposed criterion stops active learning at the appropriate timing for various models and datasets.

New method stabilizes deep neural networks by setting Lyapunov exponent to zero.

problem Stability issues in deep neural networks with low width.
method Lyapunov initialization method to set Lyapunov exponent to zero.
result Lyapunov exponent governs stability of deep networks; standard methods fail for low width.

The paper examines stability of ReLU networks in tangent space and activation regions.

problem Stability and sensitivity of ReLU networks to small changes.
method Tangent sensitivity measure for ReLU networks, focusing on stability induced by individual examples.
result Tangent sensitivity correlates with the distribution of activation regions and generalization gap.

New activation function BrownianReLU improves LSTM network performance on financial time series.

problem Gradient instability in noisy financial time series data.
method Introduces BrownianReLU, a stochastic activation function based on Brownian motion.
result Significantly improved predictive accuracy and generalization on financial datasets.

We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modeling and phoneme recognition, and outperfor…

2015-11-26abs ↗pdf ↗

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.

Recurrent neural networks trained on regular languages exhibit stable states that can recover from noise.

problem Stability of internal states in recurrent neural networks trained on regular languages.
method Empirical study with analysis of network activation and transitions between states.
result Recurrent neural networks trained on regular languages can recover from random perturbations and maintain stable states.

Novel approach analyzes ReLU networks' training dynamics and proposes GmP for improved optimization.

problem Stochastic optimization instability in ReLU networks impedes convergence and generalization.
method Characteristic activation boundaries analysis and Geometric Parameterization (GmP) technique.
result GmP resolves instability, leading to better optimization, convergence, and generalization.

Market activity scales near a constant of 0.632 in intrinsic time.

problem Understanding the stability of market scaling laws.
method Modeling market directional changes as a memoryless exponential hazard process and identifying the intrinsic time scaling constant.
result The intrinsic time scaling constant is 11/e=0.6321 - 1/e = 0.632.

Enhances activity recognition in wearable computing with context awareness and uncertainty quantification.

problem Context-dependent activity recognition and unknown contexts in wearable computing.
method Developed the α-{eta} network coupled with uncertainty quantification (UQ) based on maximum entropy.
result Improved accuracy and F-score by 10% through high-level context identification.

Meta-learning algorithms are studied for their data efficiency in personalized federated learning.

problem Data efficiency in meta-learning algorithms.
method Algorithmic stability techniques to derive bounds on transfer risk and a new evaluation framework.
result Different meta-learning methods require varying amounts of supervision for effective generalization.

Backpropagation-free RL method trains layers using local signals.

problem Vanishing or exploding gradients in backpropagation-based RL.
method Local pairwise distance matching for layer-wise training without backpropagation.
result Backpropagation-free method achieves competitive performance and stability.

GNMR controls runtime stability in low-precision language model training.

problem Efficient low-precision training faces numerical risks at specific operators.
method GNMR compares gradient norms to historical means, applying bounded recovery actions.
result GNMR preserves high-fidelity quality with sparse, budgeted recovery.

We propose a novel Shapley value approach to help address neural networks' interpretability and "vanishing gradient" problems. Our method is based on an accurate analytical approximation to the Shapley value of a neuron with ReLU activation. This analytical approximation admits a linear propagation of relevance across …

2019-09-13abs ↗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.

This work shows MLPs can approximate monotonic functions without bounded activations.

problem Optimizing MLPs with monotonic constraints and bounded activations.
method Generalized theoretical results showing MLPs with non-negative weights and saturating activations are universal approximators.
result MLPs with non-negative weights and saturating activations are universal approximators for monotonic functions.

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…

2020-01-10abs ↗pdf ↗

RELTA-SGLD stabilizes nonconvex SGLD updates with a lighter taming scheme.

problem Stabilizing superlinear stochastic-gradient updates in nonconvex optimization.
method Threshold-based taming with relative-growth principle for stability.
result Polynomial moment stability and first-order stationary accuracy in nonconvex SGLD.

Paper presents neural network controllers for offset-free setpoint tracking.

problem Offset-free setpoint tracking using neural network controllers.
method Exploiting slope-restricted activation functions, linear matrix inequalities are used to verify stability.
result Global and local stability conditions for neural network controllers are derived.

Within the natural language processing (NLP) community, active learning has been widely investigated and applied in order to alleviate the annotation bottleneck faced by developers of new NLP systems and technologies. This paper presents the first theoretical analysis of stopping active learning based on stabilizing pr…

2015-04-23abs ↗pdf ↗

The paper examines stability of shares in Proof of Stake protocol, identifying different investor behaviors and phase transitions.

problem Stability of shares in Proof of Stake protocol.
method Identification of large, medium, and small investors under various rewarding schemes; dynamical population model analysis.
result Phase transitions and thresholds for stability are characterized; chaotic centralization leads to concentration of shares.

A new activation function improves credit scoring accuracy for imbalanced datasets.

problem Imbalanced datasets in credit scoring lead to underestimation of misclassification costs.
method Introduces ASIG, an asymmetric adjusted Sigmoid function.
result ASIG-embedded classifier outperforms traditional classifiers across various imbalance ratios.

Generative model predicts daily activity sequences with duration-aware dynamics.

problem Accurately forecasting granular daily activity sequences for energy demand.
method Hierarchical semi-Markov models with duration-aware dynamics.
result Explicitly modeling activity durations improves predictive performance.

Flashback Learning balances model stability and plasticity in continual learning.

problem Balancing model stability and plasticity in continual learning.
method Flashback Learning (FL) uses a bidirectional regularization approach to balance stability and plasticity.
result FL improves model accuracy by up to 4.91% in Class-Incremental and 3.51% in Task-Incremental settings.

The paper investigates polynomial alternatives to softmax in transformer models.

problem The effectiveness of softmax attention in transformers is questioned.
method The authors explore polynomial activations as alternatives to softmax, focusing on their ability to regularize the attention matrix.
result Certain polynomials can serve as effective substitutes for softmax in transformer applications, achieving strong performance.

New method improves generalization in deep learning models.

problem Improving generalization in overparameterized deep neural networks.
method Stochastic Gauss-Newton method with Levenberg-Marquardt damping and mini-batch sampling.
result Established finite-time convergence and non-asymptotic generalization bounds.

Unified framework for robust causal directionality in quantum systems under MNAR observation.

problem Determining causal directionality in quantum systems under MNAR observation.
method Integrates CVAE-based latent constraints, MNAR-aware selection models, GEE-stabilized regression, penalized empirical likelihood, and Bayesian optimization.
result Achieves lower bias and variance, near-nominal coverage, and superior quantum-specific diagnostics.

EAGLE improves reproducibility and stability of model explanations.

problem Creating reliable explanations for opaque machine learning models.
method Formulates perturbation selection as an information-theoretic active learning problem.
result EAGLE learns a linear surrogate model with feature importance scores and uncertainty estimates.

Persistent homology analysis provides means to capture the connectivity structure of data sets in various dimensions. On the mathematical level, by defining a metric between the objects that persistence attaches to data sets, we can stabilize invariants characterizing these objects. We outline how so called contour fun…

2019-06-11abs ↗pdf ↗