New method trains neural networks with threshold activation functions efficiently.
problem Training neural networks with threshold activation functions is challenging due to zero gradients.
method We study weight decay regularized training problems of deep neural networks with threshold activations, showing they can be formulated as convex optimization problems.
result Regularized deep threshold network training problems can be formulated as standard convex optimization problems, paralleling the LASSO method.
New RGraSP framework for efficient non-convex optimization.
problem Large-scale non-convex sparsity-constrained optimization problems.
method Relaxed gradient support pursuit with semi-stochastic gradient hard thresholding.
result Our algorithms converge faster with lower per-iteration cost.
Study uses SGD to learn optimal thresholds for buying and selling stocks.
problem Optimizing investment strategies in fluctuating stock prices.
method Applying Kiefer--Wolfowitz Stochastic Gradient method to threshold strategies.
result Algorithm converges to log-optimal solution for threshold strategies.
Improved learning bounds for corrupted data using thresholded gradient descent.
problem Learning from corrupted data with adversarial noise.
method Thresholded gradient descent for sigmoidal, leaky-ReLU, and ReLU activations.
result Improved approximation bounds for various activation functions.
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 2/η. AutoClip automatically adjusts gradient clipping for better audio separation.
problem Improving generalization in audio source separation networks.
method Adaptive gradient clipping based on historical gradient norms.
result Improves generalization performance in audio source separation networks.
In this paper, we study the proximal gradient algorithm with extrapolation for minimizing the sum of a Lipschitz differentiable function and a proper closed convex function. Under the error bound condition used in [19] for analyzing the convergence of the proximal gradient algorithm, we show that there exists a thresho…
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…
SoftAD improves classification accuracy with less fine-tuning and fewer computational costs.
problem Improving classification accuracy with less fine-tuning and fewer computational costs.
method SoftAD is a softened, pointwise mechanism that downweights borderline points and limits the effects of outliers.
result SoftAD achieves classification accuracy competitive with flooding and SAM, with a smaller loss generalization gap and model norm.
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 …
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.
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.
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.
Efficient distributed learning with Byzantine-resilient thresholding and error feedback.
problem Byzantine-resilient distributed learning with communication efficiency.
method Simple thresholding for Byzantine mitigation, compressed gradients and norms for aggregation, error feedback.
result Statistical error rate matches Yin et al.~\cite{dong} but with simpler schemes, and improved convergence with error feedback.
LTP learns per-layer thresholds for efficient pruning of deep networks.
problem Efficiently pruning deep neural networks to reduce computational cost and size.
method LTP learns thresholds via gradient descent, making pruning computationally efficient and scalable.
result LTP achieves competitive compression rates and maintains high accuracy on ImageNet networks.
This paper improves convergence guarantees for gradient clipping in deep learning.
problem Improving convergence guarantees for gradient clipping in deep learning models.
method Analyzes and provides precise convergence guarantees for arbitrary clipping thresholds.
result Shows tight convergence guarantees for clipped stochastic gradient descent.
Noise in linear networks minimizes sharpness and leads to shrinkage-thresholding.
problem Minimizing sharpness in diagonal linear networks.
method Stochastic sharpness-aware minimization (SAM) with isotropic noise.
result Noise forces shrinkage-thresholding of true parameters.
Quantile gradient boosted trees outperform other models in predicting NO2 concentration distributions.
problem Forecasting high NO2 concentration episodes for effective air quality management.
method Compared 10 probabilistic forecasting models for NO2 concentration prediction.
result Quantile gradient boosted trees model outperformed others in predicting NO2 concentration distributions.
Meta-gradient D4PG optimizes performance and constraint adherence in RL.
problem Balancing performance and adherence to complex constraints in RL.
method Uses meta-gradients to find a balance between expected return and minimizing constraint violations.
result Meta-gradient D4PG consistently outperforms baselines across MuJoCo domains.
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.
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.
Gradient flows of neural networks converge to optimal values or diverge, with thresholds and asymptotic behaviors.
problem Understanding the convergence and divergence of gradient flows in neural networks.
method Analysis of gradient flows on loss landscapes of neural networks using o-minimal structures.
result Gradient flows either converge to optimal values or diverge to infinity, with thresholds and asymptotic behaviors.
In this paper we study the performance of the Projected Gradient Descent(PGD) algorithm for ℓp-constrained least squares problems that arise in the framework of Compressed Sensing. Relying on the Restricted Isometry Property, we provide convergence guarantees for this algorithm for the entire range of $0\leq p\…
DeepTopPush improves accuracy at the top for complex classification tasks.
problem Minimizing irrelevant samples above a threshold in binary classification.
method Proposes a new method for end-to-end training of deep networks to minimize loss at the top.
result Demonstrates excellent performance on visual recognition and real-world applications.
Sparse GCA finds linear relationships in multiple datasets, using gradient descent.
problem Finding linear relationships across multiple datasets with sparse loading vectors.
method Formulated as generalized eigenvalue problems, used a thresholded gradient descent algorithm.
result Proposed algorithm yields tight estimation error bounds and demonstrates effectiveness on synthetic datasets.
We consider the problem of sparsity-constrained M-estimation when both explanatory and response variables have heavy tails (bounded 4-th moments), or a fraction of arbitrary corruptions. We focus on the k-sparse, high-dimensional regime where the number of variables d and the sample size n are related through $…
A novel algorithm optimizes sparsity in reservoir computing inspired by insect brain.
problem Optimizing sparsity in reservoir computing networks.
method Inspired by insect brain, the algorithm optimizes sparsity levels by adjusting node firing thresholds.
result The algorithm outperforms standard gradient descent on tasks involving better classification, memorization, and convergence.
New method improves convergence of SGD for heavy-tailed noise.
problem Heavy-tailed noise in machine learning applications.
method Normalized SGD (NSGD) to handle heavy-tailed noise.
result Improved sample complexity and high-probability convergence.
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.
SpaRCe optimizes reservoir computing by learning neuron thresholds to improve performance and prevent forgetting.
problem Improving performance and preventing forgetting in reservoir computing networks.
method Integrates neuron-specific learnable thresholds to optimize sparsity without altering dynamics, learning read-out weights and thresholds via gradient rule.
result Threshold learning improves performance and alleviates catastrophic forgetting.
AIHT improves online high-dimensional quantile regression by separating support discovery and refinement.
problem Online high-dimensional quantile regression with structural sparsity.
method Adaptive Iterative Hard Thresholding (AIHT) alternates stochastic updates with adaptive hard-thresholding steps.
result AIHT achieves logarithmic regret for the sliding-window objective in high-dimensional settings.
Review of gradient-based algorithms in statistical inference problems.
problem Understanding the dynamics of gradient-based algorithms in statistical inference.
method Insights from physics of glassy systems.
result Quantitative and qualitative understanding of algorithm performance.
Distributed implementations of gradient-based methods, wherein a server distributes gradient computations across worker machines, suffer from slow running machines, called 'stragglers'. Gradient coding is a coding-theoretic framework to mitigate stragglers by enabling the server to recover the gradient sum in the prese…
Azure (the cloud service provided by Microsoft) is composed of physical computing units which are called nodes. These nodes are controlled by a software component called Fabric Controller (FC), which can consider the nodes to be in one of many different states such as Ready, Unhealthy, Booting, etc. Some of these state…
Variable selection in linear models plays a pivotal role in modern statistics. Hard-thresholding methods such as l0 regularization are theoretically ideal but computationally infeasible. In this paper, we propose a new approach, called the LAGS, short for "least absulute gradient selector", to this challenging yet i…
A framework for binary classification on top samples.
problem Binary classification problems above/below a threshold.
method General framework for ranking problems, hypothesis testing.
result Theoretical and numerical analysis of methods.
Designing deterministic denominators for SGLD stabilizes large drifts.
problem Stabilizing large drifts in SGLD
method Using state-dependent envelopes and empirical quantiles for activation thresholds
result Proxy-quantile denominators are close to oracle-score behavior and improve deterministic taming choices
The MBO scheme for data clustering is analyzed in the large data limit, proving convergence to optimal partition problems.
problem Analyzing the MBO scheme for data clustering in the large data limit.
method Implicit gradient descent on the thresholding energy of a similarity graph.
result The MBO scheme outcomes converge to minimizers of a weighted optimal partition problem.
SAD-DPSGD improves model performance on imbalanced medical datasets like HAM10000.
problem Data leakage and imbalanced distribution in medical image classification datasets.
method SAD-DPSGD uses a linear decaying mechanism for noise and clipping thresholds to enhance performance.
result SAD-DPSGD outperforms Auto-DPSGD on HAM10000, improving accuracy by 2.15%.
Iterative thresholding algorithms are well-suited for high-dimensional problems in sparse recovery and compressive sensing. The performance of this class of algorithms depends heavily on the tuning of certain threshold parameters. In particular, both the final reconstruction error and the convergence rate of the algori…
New algorithm for active exploration in bandit problems.
problem Active exploration in bandit problems.
method Gradient ascent with online lazy mirror ascent sampling rule.
result Asymptotically optimal and computationally efficient.
Gradient descent forces neural network eigenvalues to a specific threshold.
problem Understanding why gradient descent drives eigenvalues to a specific threshold.
method Introduced edge coupling, a functional on consecutive iterate pairs, to explain the trajectory towards the eigenvalue threshold.
result Gradient descent forces the Hessian eigenvalue to the threshold 2/η from arbitrary initialization. IHT improves sparse distribution learning.
problem Learning sparse discrete distributions.
method Iterative hard thresholding as a solution, with a greedy approximate projection.
result IHT achieves state of the art results for sparse distribution learning.
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.
Study on gradient clipping in SGD for high-dimensional problems.
problem Understanding and optimizing gradient clipping in high-dimensional machine learning models.
method Theoretical analysis of streaming SGD with gradient clipping in a least squares problem, focusing on large intrinsic dimensionality.
result Developed a deterministic equation to describe the loss evolution in clipped SGD, showing benefits under certain conditions.
Mathematical model describes how red blood cells return to equilibrium.
problem How red blood cells regain equilibrium after deformation.
method Gradient flow of the Canham-Helfrich functional, proving global existence and convergence for spheres and axisymmetric tori.
result Global existence and convergence of smooth solutions for spheres and axisymmetric tori under specific energy conditions.
We study --both in theory and practice-- the use of momentum motions in classic iterative hard thresholding (IHT) methods. By simply modifying plain IHT, we investigate its convergence behavior on convex optimization criteria with non-convex constraints, under standard assumptions. In diverse scenaria, we observe that …
The use of M-estimators in generalized linear regression models in high dimensional settings requires risk minimization with hard L0 constraints. Of the known methods, the class of projected gradient descent (also known as iterative hard thresholding (IHT)) methods is known to offer the fastest and most scalable sol…