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.

168,694 papers · 148 categories

Trend · papers per month

228456683911 · Jun 202019922001200920172026
48 results for stability improvements

Enhanced stability improves privacy in machine learning.

problem Improving privacy in machine learning training while maintaining accuracy.
method Study of stability in private empirical risk minimization, focusing on strongly-convex loss functions and uniform stability.
result An algorithm with uniform stability of β implies a bound of O(√β) on the scale of noise required for differential privacy.

Improved RL algorithm stabilizes unknown linear systems with polynomial regret.

problem Learning and stabilizing unknown linear dynamical systems.
method Proposes an algorithm with an improved exploration strategy for fast stabilization.
result Achieves ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) regret after TT time steps.

Enhances stability ranges for Torelli and congruence subgroup homologies.

problem Improving stability ranges for specific subgroup homologies.
method Analyzes H2(Torelli subgroup of Aut(Fn)'s), H2(Torelli subgroup of mapping class groups), and Hk(congruence subgroups of GL_n(R)'s).
result Improved central stability ranges for various subgroup homologies.

Stacking is a general approach for combining multiple models toward greater predictive accuracy. It has found various application across different domains, ensuing from its meta-learning nature. Our understanding, nevertheless, on how and why stacking works remains intuitive and lacking in theoretical insight. In this …

2019-01-26abs ↗pdf ↗

Paper improves stability analysis of SGD for various loss functions and data distributions.

problem Improving stability analysis of SGD for non-convex loss functions and data distributions.
method Analyzes stability of SGD for convex and non-convex loss functions, and improves data-dependent bounds.
result Improved stability bounds for non-convex loss functions and convex regularized loss functions.

New bounds improve generalization in learning scenarios.

problem Limitations of existing information-theoretic bounds in SCO problems.
method Sample-conditioned hypothesis stability and neighboring-hypothesis matrix.
result Sharper generalization guarantees in various learning scenarios.

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.

Paper proposes a new framework to improve stability-based bounds in deep learning.

problem Explaining generalization in overparameterized neural networks.
method Decomposes excess risk dynamics into signal and noise components, applying stability-based bounds only to the noise.
result The decomposition framework improves stability-based bounds and explains generalization in neural networks.

We prove that the quotient map from Aut(F_n) to Out(F_n) induces an isomorphism on homology in dimension i for n at least 2i+4. This corrects an earlier proof by the first author and significantly improves the stability range. In the course of the proof, we also prove homology stability for a sequence of groups which a…

2004-06-18abs ↗pdf ↗

This paper improves forecast stability without sacrificing accuracy using dynamic loss weighting.

problem Rolling origin forecast instability in time series forecasting.
method Dynamic loss weighting algorithms applied to the N-BEATS model.
result Dynamic loss weighting can further improve forecast stability without compromising accuracy.

We describe partial semi-simplicial resolutions of moduli spaces of surfaces with tangential structure. This allows us to prove a homological stability theorem for these moduli spaces, which often improves the known stability ranges and give explicit stability ranges in many new cases. In each of these cases the stable…

2009-09-23abs ↗pdf ↗

New algorithm stabilizes RL policy learning through divergence regularization.

problem Stabilize policy learning and improve performance in RL.
method Proximity term constraining discounted state-action visitation distributions to be close to each other.
result Proposed algorithm improves stability and final performance in RL tasks.

New stability measures for similar features improve feature selection accuracy.

problem Existing stability measures fail to distinguish similar features in highly correlated datasets.
method Introduce new adjusted stability measures that consider feature similarities.
result One new stability measure considers highly similar features as interchangeable.

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.

Spectral normalization stabilizes GANs by controlling gradient explosion and vanishing.

problem Stability and sample quality issues in GAN training.
method Spectral normalization controls gradient explosion and vanishing, improving GAN training stability and sample quality.
result Bidirectional Scaled Spectral Normalization (BSSN) outperforms standard spectral normalization in sample quality and training stability.

We give a complete and detailed proof of Harer's stability theorem for the homology of mapping class groups of surfaces, with the best stability range presently known. This theorem and its proof have seen several improvements since Harer's original proof in the mid-80's, and our purpose here is to assemble these many a…

2010-06-23abs ↗pdf ↗

This paper enhances stability selection by evaluating overall results robustness and identifying optimal regularization values.

problem Improving the robustness and reliability of high-dimensional variable selection.
method Developed a stability estimator to evaluate stability of stability selection results, calibrating key parameters.
result Identified optimal regularization value and improved stability of variable selection.

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.

New method stabilizes machine learning predictions across random seeds.

problem Machine learning predictions vary across random seeds, causing instability.
method Introduces adaptive cross-bagging to eliminate seed dependence.
result Adaptive cross-bagging achieves targeted stability in debiased machine learning.

New stability theorem for hyperbolic metrics without volume bounds.

problem Stability of finite volume hyperbolic metrics without upper volume bounds.
method Abstract axiomatic framework and bootstrap argument to extend stability result.
result Weaker exponential control of the metric allows for a broader application of the stability theorem.

To date, the instability of prognostic predictors in a sparse high dimensional model, which hinders their clinical adoption, has received little attention. Stable prediction is often overlooked in favour of performance. Yet, stability prevails as key when adopting models in critical areas as healthcare. Our study propo…

2016-09-28abs ↗pdf ↗

Paper improves zero-shot protein stability prediction by clarifying free-energy foundations.

problem Improving zero-shot protein stability prediction using inverse folding models.
method Clarifying the free-energy foundations of inverse folding models and proposing better estimates of relative stability.
result Significant gains in zero-shot performance can be achieved with simple methods.

ABM simulates OTC government bond market dynamics, enhancing liquidity and stability.

problem Understanding and ensuring market stability and liquidity in OTC government bond markets.
method Developed a bespoke ABM to simulate market-maker interactions and test hypotheses.
result Greater agent diversity enhances market liquidity and reducing market-making costs improves stability.

SIM-Shapley improves SV approximation efficiency and stability.

problem High computational costs of Shapley value methods in high-dimensional settings.
method Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley).
result Reduced computation time by up to 85% while maintaining feature attribution quality.

DHLNN improves deep hedging for financial derivatives with faster convergence and better stability.

problem Challenges in computational inefficiency, sensitivity to noisy data, and optimization complexity in deep hedging methods.
method Integrates periodic fixed-gradient optimization and linearized training dynamics to stabilize and accelerate deep learning model training.
result Demonstrates faster convergence, improved stability, and superior hedging performance across diverse market scenarios.

MARL improves LBM stability and accuracy across scales.

problem Stability and accuracy issues in under-resolved LBM simulations.
method Multi-Agent Reinforcement Learning (MARL) to dynamically control local relaxation parameters.
result MARL closures stabilize simulations and recover spectra of fully resolved models.

DTM improves dLLM fine-tuning stability and performance.

problem Intractable sequence-level marginal likelihoods for masked diffusion models.
method Discrete Tilt Matching (DTM) recasts dLLM fine-tuning as state-level matching of local unmasking posteriors under reward tilting.
result DTM yields strong gains on Sudoku and Countdown while remaining competitive on MATH500 and GSM8K.

Noise in RNNs promotes flatter minima and more stable dynamics.

problem Understanding and optimizing the training of RNNs with noise.
method Formalizing RNNs as stochastic differential equations and analyzing the effect of noise in the hidden states.
result Noise injection in RNNs leads to flatter minima, more stable dynamics, and improved robustness.

A new GAN loss function based on cumulant generating functions improves stability and robustness.

problem Improving the stability and performance of GANs.
method Cumulant GAN loss function based on variational R{é}nyi divergence.
result Cumulant GAN achieves linear convergence to Nash equilibrium and superior performance in image generation.