Non-deterministic policy improvement stabilizes reinforcement learning methods.
problem Instability in greedy policy improvement in approximated reinforcement learning.
method Non-deterministic policy improvement and suitable value function representation.
result Non-deterministic policy improvement stabilizes LSPI and other reinforcement learning methods.
The paper analyzes how stacking improves model stability.
problem Lack of theoretical insight into how stacking works.
method Stability analysis of learning algorithms, focusing on hypothesis stability.
result The hypothesis stability of stacking is a product of base models and combiner.
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.
Feature bagging improves stability through random feature subsampling.
problem Improving the stability of ensemble learning methods.
method Introducing feature instability (FI) and analyzing feature bagging in parametric and model-free settings.
result Feature bagging provides stronger stability than non-bagged methods, especially with aggressive subsampling.
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 i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) regret after T T T time steps. The paper improves decision tree stability for health care applications.
problem Stability of decision trees in health care applications.
method Introducing a new distance metric to determine tree stability and proposing a novel training methodology.
result On average, a 4.6% decrease in predictive power yields a 38% increase in model stability.
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.
Unified techniques improve stability and replicability in changing data.
problem Concept drift in data generating distribution.
method Removing hidden confounding and causal regularization.
result Improves stability, replicability, and robustness in heterogeneous data.
New method improves feature selection by integrating stability paths.
problem Improving feature selection with tighter false positive control.
method Integrating stability paths to strengthen theoretical bounds on E(FP).
result Significantly more true positives with same E(FP) control.
New defense improves numerical stability in regression networks.
problem Adversarial attacks on regression neural networks.
method Formulated a stability-inducing regularization defense.
result Defense outperforms prior approaches and improves numerical stability.
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.
Copula-based normalizing flows improve flexibility and stability for heavy-tailed data.
problem Limited expressive power of vanilla normalizing flows.
method Generalize base distribution to copula for more accurate representation of target distribution.
result Copula-based normalizing flows improve flexibility, stability, and effectiveness for heavy-tailed data.
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.
We improve neural network robustness verification by training for faster stability.
problem Efficient verification of adversarial robustness in deep networks.
method Co-design of weight sparsity and ReLU stability to simplify verification.
result Improving ReLU stability leads to a 4-13x speedup in verification times.
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.
New quasimetric spaces improve stability in complex Hessian equations.
problem Improving stability results for complex Hessian equations.
method Constructing a family of quasimetric spaces in generalized potential theory.
result Convergence of quasimetric spaces leads to improved stability results.
Improves reinforcement learning stability and efficiency.
problem Combining stability and efficiency in reinforcement learning.
method Combines on-policy stability with off-policy sample reuse.
result Demonstrates improved performance in both theory and practice.
Enhanced Particle Swarm Optimization improves ANN classification accuracy and stability.
problem Improving classification accuracy of ANN models.
method Proposes an enhanced Particle Swarm Optimization for ANN training.
result Significant improvement in classification accuracy through stability analysis.
Improved MLE for Hawkes Processes stabilizes unstable optimization.
problem Unstable Maximum Likelihood Estimation (MLE) for Hawkes Processes.
method Simple stabilization procedure to improve MLE without restrictive assumptions.
result Stabilized MLE outperforms traditional methods over various sequence lengths.
Stability training improves deep neural networks' robustness without data augmentation.
problem Improving deep neural networks' robustness against input perturbations.
method Stability training as an alternative to data augmentation.
result Stability training outperforms data augmentation in specific transformations and offers improved robustness against a broader range of distortions.
WGAN improves GAN stability and solves mode collapse.
problem Stability and mode collapse issues in GANs.
method Introduces WGAN, a new algorithm with improved stability and mode handling.
result WGAN solves mode collapse and improves stability.
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…
SmoothDARTS stabilizes DARTS-based architecture search by smoothing loss landscapes.
problem DARTS-based NAS methods suffer from instability, leading to deteriorating architectures.
method SmoothDARTS (SDARTS) uses perturbation-based regularization to smooth the loss landscape.
result SmoothDARTS improves the generalizability and performance of DARTS-based methods.
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…
SAM improves generalization by operating near the edge of stability.
problem Improving generalization in neural networks.
method Sharpness-Aware Minimization (SAM) approach to training neural networks.
result SAM operates near the 'edge of stability' identified by the analysis.
The paper improves asymptotic polybalanced kernels for extremal Kaehler metrics.
problem Stability and metrics on algebraic manifolds.
method Asymptotic polybalanced kernels associated to extremal Kaehler metrics.
result Stronger asymptotic relative Chow-polystability for extremal Kaehler polarized algebraic manifolds.
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.
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.
The paper examines how random seed affects model stability and proposes ASWA and NASWA techniques to improve model robustness.
problem The impact of random seed on model performance and stability.
method A controlled study on attention, gradient-based, and surrogate model interpretations. Proposed techniques: Aggressive Stochastic Weight Averaging (ASWA) and Norm-filtered Aggressive Stochastic Weight Averaging (NASWA).
result Improvement in model robustness with ASWA and NASWA techniques, reducing standard deviation of model performance by 72%.
Improves stability of actor-critic methods by penalizing TD error.
problem Instability in actor-critic methods during learning.
method Regularize actor's learning objective by penalizing critic's TD error.
result Improves stability and overall performance of actor-critic methods.
Noise stability improves understanding of Transformer models.
problem Lack of robustness metrics for real-valued domains and junta-like input dependence in modern LLMs.
method Proposed noise stability as a new metric and developed a practical regularization method.
result Noise stability regularization method accelerates training by 35-75%.
Averaged-DQN stabilizes DRL by averaging Q-values.
problem Instability and variability in DRL algorithms.
method Averaging previously learned Q-values estimates.
result Significantly improved stability and performance.
A fast method estimates stability of ensemble feature selectors.
problem Improving stability of ensemble feature selectors for better prediction.
method Simulator of a feature selector to estimate stability.
result Reduces computation time for estimating stability.
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.
Improved stability and generalization for blackbox learned optimizers.
problem Stability and generalization issues in blackbox learned optimizers.
method Investigation using dynamical systems, modifications to optimizer architecture and meta-training procedure.
result Improved stability and generalization of learned optimizers.
New deep architecture improves stability and robustness of neural networks.
problem Improving stability and robustness of neural networks.
method Proposes a new deep architecture using implicit residual blocks with fixed point definitions.
result Improved stability and generalization power with fewer hyperparameters.
In this short article, we improve the dynamical stability and instability results for Ricci-flat metrics under Ricci flow proved by Sesum and Haslhofer, getting rid of the integrability assumption.
Stochastic ensembling improves stability in training Generative Adversarial Networks.
problem Oscillation, mode collapse, and imbalance between generator and discriminator.
method Stochastic ensembling of neural networks.
result Improves stability and learning capacity of GANs.
Improves Lasso's stability in correlated predictor settings.
problem Lasso's selection stability deteriorates with correlated predictors.
method Integrates a weighting scheme into the Lasso penalty function, using a correlation-adjusted ranking.
result Demonstrates improved selection stability on simulated and real-world datasets.
AKO improves stability and power of Knockoff inference.
problem Instability of Knockoff-based inference.
method Aggregation of Multiple Knockoffs (AKO) method.
result AKO maintains FDR control while improving stability and power.
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.
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…
MAGAN improves GANs stability and performance with adaptive hinge loss.
problem Improving stability and performance of GANs.
method Adaptive hinge loss function with estimated margin based on target distribution energy.
result MAGAN converges to global optimum under certain assumptions.
Improved stable RNNs trained faster with less expressibility trade-off.
problem Stable recurrent neural networks are hard to train without sacrificing expressibility.
method Implicit model structure with contraction analysis for stable models.
result Significant increase in training speed and model performance.
Residual networks improve noise stability, leading to better performance.
problem Degradation problem in training Residual Neural Networks.
method Introduced simplified versions of ResNets and PlnNets, showing equivalence in expressive power.
result Residual networks have better noise stability, leading to improved generalization.