Sparse coding is typically solved by iterative optimization techniques, such as the Iterative Shrinkage-Thresholding Algorithm (ISTA). Unfolding and learning weights of ISTA using neural networks is a practical way to accelerate estimation. In this paper, we study the selection of adapted step sizes for ISTA. We show t…
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
48 results for “Step Size Threshold”
The paper analyzes RLVR's training dynamics, proving convergence depends on aligning update direction with Gradient Gap.
problem Understanding why RLVR works and its limitations.
method Analysis of RLVR's training process at trajectory and token levels, introducing Gradient Gap.
result Convergence depends on aligning update direction with Gradient Gap, with a sharp step-size threshold.
Neurally Augmented ALISTA improves sparse reconstruction performance.
problem Improving sparse reconstruction performance with theoretical guarantees and empirical improvements.
method Integrates an LSTM network to compute adaptive step sizes and thresholds for each target vector during reconstruction.
result Empirical performance is further improved, especially as compression ratios become more challenging.
This paper analyzes convergence of DP-SGD with adaptive quantile clipping.
problem Empirical success of adaptive clipping methods lacks theoretical understanding.
method Comprehensive convergence analysis of SGD with quantile clipping (QC-SGD).
result Establishes theoretical guarantees for DP-QC-SGD, revealing relationships between quantile selection, step size, and convergence.
SubTSBR to tackle high noise and outliers for data-driven discovery of differential equationsstat.ML
Data-driven discovery of differential equations has been an emerging research topic. We propose a novel algorithm subsampling-based threshold sparse Bayesian regression (SubTSBR) to tackle high noise and outliers. The subsampling technique is used for improving the accuracy of the Bayesian learning algorithm. It has tw…
We consider the dynamics of a linear stochastic approximation algorithm driven by Markovian noise, and derive finite-time bounds on the moments of the error, i.e., deviation of the output of the algorithm from the equilibrium point of an associated ordinary differential equation (ODE). We obtain finite-time bounds on t…
Improved Sparse Polyak for high-dimensional M-estimation with sparser solutions.
problem High-dimensional M-estimation problems with potential loss of sparsity and accuracy.
method Variant of Sparse Polyak with optimal thresholding operators.
result Retains desirable scaling properties while achieving sparser and more accurate solutions.
Reward-poisoning attacks can force RL agents to learn bad policies, and we categorize and quantify their feasibility.
problem Reward-poisoning attacks can manipulate RL agents to learn undesirable policies.
method Categorize attacks by infinity-norm constraint, provide thresholds for feasibility, and develop adaptive attack strategies.
result Adaptive reward-poisoning attacks can achieve the nefarious policy in polynomial steps, while non-adaptive attacks require exponential steps.
Paper proposes SRA algorithm for online learning robustness and adaptivity.
problem Quantifying and evaluating tradeoff between robustness and adaptivity in online learning.
method SRA algorithm using biased stochastic approximation scheme with adaptive threshold.
result SRA algorithm provides superior performance in synthetic and real datasets.
Paper finds exact recovery threshold in general hypergraph model.
problem Exact recovery of communities in general hypergraph model.
method Developed a two-stage polynomial-time algorithm for exact recovery.
result Sharp threshold for exact recovery in terms of generalized Chernoff-Hellinger divergence.
Iterative thresholding algorithms seek to optimize a differentiable objective function over a sparsity or rank constraint by alternating between gradient steps that reduce the objective, and thresholding steps that enforce the constraint. This work examines the choice of the thresholding operator, and asks whether it i…
Gradient descent near stability threshold exhibits sharpness oscillations.
problem Understanding sharpness behavior near stability threshold in non-Euclidean norms.
method Interpreted EoS through Directional Smoothness and generalized sharpness under arbitrary norms.
result Non-Euclidean GD with generalized sharpness shows sharpness oscillations near .
New algorithm robustly estimates sparse models in high dimensions with corrupted data.
problem Estimating latent variable models with arbitrarily corrupted samples in high dimensional space.
method Trimmed (Gradient) Expectation Maximization with trimming gradients and hard thresholding steps.
result The algorithm converges to near optimal statistical rate geometrically under certain conditions.
Monotone neural networks can approximate and interpolate functions efficiently.
problem Understanding the efficiency and expressiveness of monotone neural networks.
method Solving the monotone interpolation problem using depth-4 networks and comparing size bounds with arbitrary networks.
result Monotone neural networks can approximate and interpolate functions efficiently, but may require exponential size in high dimensions.
WALNUTS improves sampling efficiency and robustness for multi-scale distributions.
problem Adapting leapfrog step size for multi-scale posterior distributions.
method Adapts leapfrog step size at fixed intervals of simulated time, selecting the largest step size to keep energy error below a threshold.
result Substantial improvements in sampling efficiency and robustness compared to standard NUTS.
Study stability thresholds of big line bundles, proving bounds and generalizing results.
problem Stability thresholds of big line bundles and their asymptotic behavior.
method Explicit bounds on error terms, using quasi-monomial valuations to compute stability thresholds.
result Proves Jin--Rubinstein--Tian's questions affirmatively.
New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.
problem Challenges in online reinforcement learning for non-episodic, finite-horizon MDPs.
method Introduces a K-step lookahead Q-function with a time-varying threshold for selecting actions.
result Achieves minimax optimal constant regret for K=1 and regret for K ≥ 2.
Paper provides linear convergence guarantees for KZIHT and KZPT methods.
problem Solving linear equation systems with sparse constraints.
method Combines Kaczmarz and iterative thresholding methods, using reshuffling data sampling.
result KZIHT and KZPT converge linearly to sparse solutions.
Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)cs.LG
Neural network quantization procedure is the necessary step for porting of neural networks to mobile devices. Quantization allows accelerating the inference, reducing memory consumption and model size. It can be performed without fine-tuning using calibration procedure (calculation of parameters necessary for quantizat…
Ordinary least squares (OLS) is the default method for fitting linear models, but is not applicable for problems with dimensionality larger than the sample size. For these problems, we advocate the use of a generalized version of OLS motivated by ridge regression, and propose two novel three-step algorithms involving l…
Transforms any test into anytime-valid with sample savings.
problem Sequential data invalidates classical test guarantees.
method Predicts test outcomes to create anytime-valid stopping rules.
result Ensures Type-I error control and near-optimal power.
Implicit Q-learning and SARSA adjust step-sizes automatically, improving stability and performance.
problem Numerical instability and slow progress in Q-learning and SARSA due to step-size calibration.
method Reformulate iterative updates as fixed-point equations, scaling step-sizes inversely with feature norms.
result Implicit methods maintain stability over broader step-size ranges and achieve comparable convergence rates.
Registration-Free Monitoring of Unstructured Point Cloud Data via Intrinsic Geometrical Propertiescs.CV
A new method monitors unstructured 3D shapes without registration.
problem Error-prone registration and mesh reconstruction steps in PCD monitoring.
method Intrinsic geometric properties of shapes, using Laplacian and geodesic distances.
result Effective monitoring of defects without registration and mesh reconstruction.
The paper explores how dynamic preconditioning affects the CLT in online averaging.
problem When does dynamic preconditioning preserve the Polyak-Ruppert CLT?
method The authors decompose the averaged error and identify a stabilization-rate threshold for the CLT to hold.
result The CLT holds if the dynamic remainder vanishes in and the stabilization rate exceeds a threshold.
In this paper, we investigate a multivariate multi-response (MVMR) linear regression problem, which contains multiple linear regression models with differently distributed design matrices, and different regression and output vectors. The goal is to recover the support union of all regression vectors using -reg…
Gradient descent near stability threshold shows sharpness oscillations.
problem Understanding sharpness and stability in non-Euclidean norms during gradient descent.
method Interpreted EoS through Directional Smoothness, defined generalized sharpness for arbitrary norms.
result Non-Euclidean GD exhibits sharpness oscillations around the stability threshold.
Proposes a method to choose thresholds for LLM evaluation metrics.
problem Ensuring reliable large language models (LLMs) with correct threshold selection.
method Identify risks, stakeholders' risk tolerance, and use ground-truth data to determine thresholds.
result Demonstrates a concrete example with the Faithfulness metric and HaluBench dataset.
New findings show GD converges to a linear interpolator even with quadratic loss function under certain conditions.
problem Understanding convergence of Gradient Descent with quadratic loss functions.
method Parameterized linear regression with quadratic loss function, empirical and theoretical analysis.
result Gradient Descent converges to a linear interpolator even with quadratic loss function under the Edge of Stability regime.
Exact recovery method for community detection in Gaussian mixtures with dependent noise.
problem Community detection in Gaussian mixtures with dependent and heterogeneous noise.
method Maximum likelihood estimator (MLE) for constrained quadratic optimization problem, using -whitened separation and local inequalities.
result Sharp exact-recovery threshold and no-gap mechanism in the unknown-size setting.
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithmquant-ph
QAOA matches classical tensor power iteration in spiked tensor model recovery.
problem Statistical estimation in spiked tensor model with computational gap.
method Analysis of QAOA performance on spiked tensor model.
result QAOA weak recovery threshold matches tensor power iteration.
A simple model explains phase transition in large language models.
problem Understanding the emergence of abilities in large language models.
method Modeling LLM as a sequence-to-sequence random function and using a list decoder.
result A critical threshold exists where the expected number of erroneous sequences grows exponentially.
Resolving a conjecture of Abbe, Bandeira and Hall, the authors have recently shown that the semidefinite programming (SDP) relaxation of the maximum likelihood estimator achieves the sharp threshold for exactly recovering the community structure under the binary stochastic block model of two equal-sized clusters. The s…
The paper analyzes fixed step-size SA schemes on Riemannian manifolds.
problem Developing efficient algorithms for optimization on curved spaces.
method Fixed step-size stochastic approximation schemes in a Riemannian framework.
result The schemes converge to the solution as the step-size approaches zero.
Hard Thresholding Pursuit (HTP) is an iterative greedy selection procedure for finding sparse solutions of underdetermined linear systems. This method has been shown to have strong theoretical guarantee and impressive numerical performance. In this paper, we generalize HTP from compressive sensing to a generic problem …
Momentum affects optimization differently at small vs large batch sizes near instability.
problem Understanding how momentum impacts optimization near the edge of stability.
method Demonstrated through batch-size dependent behavior of SGD with momentum.
result Momentum operates in two distinct regimes: amplifying stochastic fluctuations at small batch sizes and stabilizing at large batch sizes.
The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies …
High-dimensional models become unstable when sample size falls below a critical level, leading to a phase transition.
problem Instability in high-dimensional learning models when sample size is insufficient.
method Proved the necessity of a Fisher eigenvalue threshold for stability, introduced Fisher floor for verification.
result A sharp phase transition between reliable concentration and inevitable failure in high-dimensional learning.
In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet few algorithms have been developed for setting the step-size automatically for TD learning. An important limitation of current methods is that…
The paper extends risk measures to two-step approximations and studies log-concave distributions.
problem Extending classical risk measures to two-step approximations.
method Optimization problem for determining optimal regime thresholds and values for log-concave distributions.
result Conditions for the uniqueness of regime changing in log-concave distributions.
New algorithm improves stability of optimization algorithms by adapting step-size.
problem Optimization algorithms' effectiveness is sensitive to step-size hyperparameters.
method Adapts NGN step-size method with momentum to enhance stability.
result Achieves convergence rate of O(1/√K) without restrictive assumptions.
AutoStep MCMC adapts step size locally for better sampling efficiency.
problem Challenging step size selection for complex, multiscale targets.
method AutoStep MCMC uses a locally adaptive step size for involutive proposals.
result AutoStep MCMC is π-invariant, irreducible, and aperiodic.
The binary symmetric stochastic block model deals with a random graph of vertices partitioned into two equal-sized clusters, such that each pair of vertices is connected independently with probability within clusters and across clusters. In the asymptotic regime of and for fixe…
Leave-One-Out Analysis for Nonconvex Robust Matrix Completion with General Thresholding Functionscs.IT
Paper analyzes robust matrix completion with efficient nonconvex method and leave-one-out analysis.
problem Robust matrix completion with sparse noise.
method Alternates between projected gradient step for low-rank and thresholding step for sparse noise.
result Achieves linear convergence for general thresholding functions.
New method calculates sensitivity of system failure probability.
problem Difficulty in computing sensitivity of failure probability.
method Monte Carlo strategy using response gradient and kernel smoothing.
result Single Monte Carlo run for sensitivity estimates.
The interplay between computational efficiency and statistical accuracy in high-dimensional inference has drawn increasing attention in the literature. In this paper, we study computational and statistical boundaries for submatrix localization. Given one observation of (one or multiple non-overlapping) signal submatrix…
We adapt the Douglas-Rachford (DR) splitting method to solve nonconvex feasibility problems by studying this method for a class of nonconvex optimization problem. While the convergence properties of the method for convex problems have been well studied, far less is known in the nonconvex setting. In this paper, for the…
The Neyman-Pearson (NP) paradigm in binary classification seeks classifiers that achieve a minimal type II error while enforcing the prioritized type I error controlled under some user-specified level . This paradigm serves naturally in applications such as severe disease diagnosis and spam detection, where people h…
I show the equivalence between a model of financial contagion and the threshold model of global cascades proposed by Watts (2002). The model financial network comprises banks that hold risky external assets as well as interbank assets. It is shown that a simple threshold model can replicate the size and the frequency o…