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.

169,051 papers · 148 categories

Trend · papers per month

17.5%35.0%52.6%70.1% · Jun 202019922001200920182026
48 results for learning algorithm stability

Paper analyzes stability and generalization of SCO algorithms.

problem Understanding how SCO algorithms perform on unseen data.
method Algorithmic stability analysis in statistical learning theory.
result Derives dimension-independent excess risk bounds for SCGD and SCSC.

We introduce a notion of algorithmic stability of learning algorithms---that we term \emph{argument stability}---that captures stability of the hypothesis output by the learning algorithm in the normed space of functions from which hypotheses are selected. The main result of the paper bounds the generalization error of…

2017-02-28abs ↗pdf ↗

We explore in some detail the notion of algorithmic stability as a viable framework for analyzing the generalization error of learning algorithms. We introduce the new notion of training stability of a learning algorithm and show that, in a general setting, it is sufficient for good bounds on generalization error. In t…

2012-12-12abs ↗pdf ↗

Bayesian algorithm stabilizes unknown continuous-time systems from unstable data.

problem Learning and stabilizing unknown continuous-time systems with uncertain dynamics.
method Bayesian learning algorithm that learns from unstable data to stabilize the system in finite time.
result The algorithm stabilizes unknown continuous-time stochastic linear systems effectively after a short time period.

The paper relaxes the stability condition to boost confidence in generalization for randomized learning algorithms.

problem The tension between uniform stability and L2L_2-stability in generalization bounds.
method Establishes in-expectation first moment generalization error bounds for L2L_2-stable randomized learning algorithms and uses subbagging to achieve near-tight exponential bounds.
result Improves generalization bounds for convex and non-convex optimization problems with SGD.

Paper proposes an unsupervised feature selection algorithm with stability guarantees.

problem Feature selection for dimension reduction and interpretability.
method Proposes a novel unsupervised feature selection algorithm with stability guarantees.
result The algorithm has superior generalization performance and stable selected features.

This paper analyzes stability of decision trees and logistic regression.

problem Stability of decision trees and logistic regression is analyzed to understand their performance and sensitivity.
method Two stability notions (hypothesis and pointwise hypothesis stability) are derived for decision trees and logistic regression. The stability of decision trees depends on the number of leaves, while for logistic regression, it depends on the smallest eigenvalue of the Hessian matrix. Upper bounds on generalization error are constructed.
result Logistic regression is not a stable learning algorithm.

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.

Stability is a general notion that quantifies the sensitivity of a learning algorithm's output to small change in the training dataset (e.g. deletion or replacement of a single training sample). Such conditions have recently been shown to be more powerful to characterize learnability in the general learning setting und…

2011-08-16abs ↗pdf ↗

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.

New stability framework relaxes boundedness assumptions for generalization bounds.

problem Overly restrictive assumptions for modern learning settings with heavy-tailed or unbounded losses.
method Develops a stability-based framework requiring only finite LpL_p moment conditions.
result Sharp generalization bounds derived for various learning paradigms.

Paper studies SGD stability and optimization error in pairwise learning.

problem Stability and optimization error of SGD for pairwise learning.
method Established stability and optimization error trade-offs for SGD in convex, strongly convex, and non-convex settings.
result Lower bounds for SGD optimization error and excess expected risk.

This paper extends stability analysis to non-convergent neural network training.

problem Generalization of neural networks whose training does not converge to fixed points.
method Introduces statistical algorithmic stability (SAS) to study non-convergent algorithms and their generalization.
result Stability of non-convergent training dynamics correlates with generalization performance.

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\em forward regret} that intuitively measures how good an online learning algorithm is if it is allowed a one-step look-ahead into the future. We show that given…

2012-11-26abs ↗pdf ↗

The study identifies conditions under which algorithmic stability explains generalization in interpolating learning systems.

problem Understanding when algorithmic stability explains generalization in interpolating learning systems.
method Modeling training as a function-space trajectory and measuring sensitivity to single-sample perturbations.
result There exist interpolating regimes with small risk where contractive sensitivity cannot hold, showing that stability is not a universal explanation.

New algorithms learn stability certificates from data, avoiding complex dynamics.

problem Synthesizing stability certificates from complex dynamical systems.
method Developed algorithms to learn certificate functions from trajectory data, establishing generalization error bounds.
result Efficiently learned certificates can be used for adaptive control.

This work explores the trade-offs between stability and accuracy in statistical estimation.

problem Understanding the statistical cost of algorithmic stability.
method Statistical decision-theoretic perspective, focusing on worst-case and average-case stability.
result Optimal stable estimators for mean estimation and regression settings are developed, revealing trade-offs between stability and accuracy.

Transformers learn algorithms for in-context learning with bounds and stability analysis.

problem Understanding and formalizing in-context learning as an algorithm learning problem.
method Formalizing ICL as a multitask learning problem, deriving generalization bounds, and analyzing stability.
result Transformers can implement near-optimal algorithms for classical regression tasks with i.i.d. and dynamic data.

New algorithm achieves small-loss bounds in online learning with improved rates.

problem Achieving strong stability in online learning algorithms.
method Introduces ρρ-separation to enforce strong stability, unifying previous approaches.
result Oracle-efficient algorithm achieves small-loss bounds with improved rates.

The EM algorithm's convergence is analyzed using Lyapunov stability theory.

problem Analyzing the convergence of the EM algorithm.
method Reinterpreting the EM algorithm as a dynamical system and applying Lyapunov stability theory.
result Asymptotic stability and convergence of the EM algorithm are established.

New study on replicability and stability in machine learning algorithms.

problem Ensuring consistent results in machine learning models without fixing randomness.
method Introduced global stability and list replicability concepts, proving their equivalence and boosting list replicability.
result Global stability can only be achieved weakly, while list replicability can be boosted to achieve high probability of consistent results.

This paper analyzes HTL using stability theory for binary classification.

problem Analyzing HTL's theoretical behavior in binary classification tasks.
method Stability analysis of regularized empirical risk minimizers.
result Derives generalization bounds for training error, excess risk, and cross-validation.

This paper analyzes the stability and generalization of triplet learning algorithms.

problem Lack of theoretical understanding of triplet learning's generalization performance.
method Stability analysis and high-probability generalization bounds for triplet learning algorithms.
result Established general high-probability generalization bound for triplet learning algorithms.

New analysis improves understanding of bilevel optimization stability and generalization.

problem Understanding how well bilevel optimization algorithms generalize.
method Algorithmic stability arguments and generalization bounds for three bilevel minimax solvers.
result Precise trade-off between algorithmic stability, generalization gaps, and practical settings.

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.

Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a consequence, learning algorithms are rarely applied on safety-crit…

2017-05-23abs ↗pdf ↗

New bounds show faster convergence for learning algorithms.

problem Improving risk bounds for learning algorithms.
method Using algorithmic stability and common assumptions like Polyak-Lojasiewicz condition, smoothness, and Lipschitz continuity.
result Achieves convergence rate of O(log2(n)/n2)O(\log^2(n)/n^2) with high probability.

This paper introduces Libra to analyze and optimize generalization in Federated Learning.

problem Inconsistent local optima in Federated Learning lead to poor generalization performance.
method Introduces Libra, a generalization dynamics analysis framework for algorithm-dependent excess risk minimization.
result Libra highlights the trade-offs between model stability and gradient norms in Federated Learning.

The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion of LqL^q stability, and the strong use of moment inequalities. LqL^q stability e…

2016-08-23abs ↗pdf ↗

New credit attribution methods for machine learning models using relaxed stability guarantees.

problem Ensuring proper attribution in generative models trained on existing works.
method Proposed new definitions of stability that allow for non-stable processing of a subset of datapoints with permission.
result Extended well-studied stability notions and provided a comprehensive characterization of learnability.

Paper derives exponential bounds for learning risk using stable hypothesis.

problem Tackles the gap between optimal and suboptimal generalization bounds.
method Uses recent advances in concentration inequalities and a weaker stability notion.
result Derives an exponential tail bound for the concentration of the estimated risk.

Randomness is crucial for stability in learning and statistics, especially for differential privacy.

problem Quantifying the amount of randomness needed for algorithmic stability.
method Weak-to-strong boosting theorem for stability, characterizing randomness complexity of PAC Learning.
result Randomness complexity is tightly controlled by the best replication probability of any deterministic algorithm solving the task.

Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.

problem Control jump-diffusion processes with unknown coefficients in reinforcement learning.
method Lipschitz continuous optimal feedback controls, stability analysis of forward-backward SDEs, least-squares algorithm.
result Achieves O(NlnN)O(\sqrt{N\ln N}) regret for linear-convex learning problems with jumps.

The paper analyzes stability and generalization of GCNNs on graphs.

problem Theoretical understanding of GCNN models' generalization properties.
method Analysis of stability and derivation of generalization guarantees for semi-supervised graph learning.
result The stability of GCNN models depends on the largest absolute eigenvalue of the graph convolution filter.

Stochastic gradient descent (SGD) is commonly used for optimization in large-scale machine learning problems. Langford et al. (2009) introduce a sparse online learning method to induce sparsity via truncated gradient. With high-dimensional sparse data, however, the method suffers from slow convergence and high variance…

2016-04-21abs ↗pdf ↗

Regularization improves generalization in Bayesian RL, shown through algorithmic stability.

problem Ensuring good generalization in Bayesian reinforcement learning.
method Algorithmic stability, using regularization and fast convergence rates for mirror descent.
result Regularization makes the optimal policy stable, improving generalization.