Proposes a gradient-based variable selection method for binary classification in RKHS.
problem Variable selection in high-dimensional data analysis.
method Gradient-based representation of large-margin classifier with group-lasso penalty.
result Selection consistency and risk bound of the estimated classifier.
Variable selection and dimension reduction are two commonly adopted approaches for high-dimensional data analysis, but have traditionally been treated separately. Here we propose an integrated approach, called sparse gradient learning (SGL), for variable selection and dimension reduction via learning the gradients of t…
New algorithm maintains privacy while improving model performance in selective release.
problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.
EGAB algorithms improve online portfolio selection.
problem Online portfolio selection problem.
method Generalized exponentiated gradient (EG) updates with Alpha-Beta divergence regularization.
result EGAB algorithms enhance portfolio performance, especially with transaction costs.
GSSBO reduces GP fitting time in Bayesian optimization.
problem High computational cost of fitting Gaussian process surrogate models in Bayesian optimization.
method Gradient-based sample selection to reduce the number of samples used in GP fitting.
result Sublinear regret bounds and significant reduction in computational cost.
Paper proposes adaptive parameter selection for KGD algorithms.
problem Improving parameter selection for kernel-based gradient descent.
method Integrates bias-variance analysis with splitting method, introduces empirical effective dimension.
result Adaptive parameter selection strategy achieves optimal generalization error bound.
A rule selects the best gradient estimator for faster convergence in machine learning.
problem Choosing the best gradient estimator for faster convergence in machine learning.
method Analyzed convergence rates of SGD as a function of time, resulting in a simple rule to select the best estimator.
result The selected estimator leads to the best optimization convergence guarantee, same for different SGD variants and objective types.
A feature selection algorithm should ideally satisfy four conditions: reliably extract relevant features; be able to identify non-linear feature interactions; scale linearly with the number of features and dimensions; allow the incorporation of known sparsity structure. In this work we propose a novel feature selection…
Equivalent tests for SGD batch size selection found.
problem Finding equivalent tests for adaptive batch size selection in SGD.
method Norm and inner product/orthogonality tests equivalence demonstration.
result Norm and inner product/orthogonality tests are equivalent under specific conditions.
A new principle for optimizer selection improves training speed and performance.
problem Finding the best optimizer hyperparameters for faster training.
method Formulate optimizer selection as maximizing the expected drop rate in loss, treating gradients and updates as signals and an optimizer as a causal filter.
result Greedy optimizer selection yields stable and effective momentum rules.
AgFlow speeds up model selection in penalized PCA.
problem Efficient model selection in penalized PCA for HDLSS settings.
method Implicit regularization effect of gradient flow to reduce computation complexity.
result AgFlow achieves the complete solution path of L2-penalized PCA.
Boosting method adapted for non-square loss functions.
problem Applying gradient boosting to non-square loss functions.
method Introducing column measure ν^(L_2) to adapt L2-Boosting for different loss functions.
result L2-Boosting can be modified to select variables according to different loss functions.
New adaptive temperature selection improves parallel tempering efficiency.
problem Enhancing mixing in multi-modal distributions using parallel tempering.
method Adaptive temperature selection using policy gradient approach.
result Lower integrated autocorrelation times achieved compared to traditional methods.
Scalable feature selection improves GBDT model training speed.
problem Efficiently selecting features for GBDT models in high-dimensional settings.
method Developed a scalable forward feature selection method using group testing.
result Significant speedups in training time with competitive model performance.
MIBoost boosts variable selection with multiple imputation.
problem Missing data complicates variable selection in statistical models.
method Gradient boosting with multiple imputation, MIBoost.
result MIBoost yields comparable predictive performance to other methods.
A scalable gradient-based framework for sparse portfolio selection.
problem Sparse minimum-variance portfolio selection with cardinality constraint.
method Gradient-based optimization with Boolean relaxation and tunable parameter.
result Matches commercial solvers in most instances, differing by a few assets with negligible error in portfolio variance.
New method optimizes hyperparameters in deep learning models efficiently.
problem Manual hyperparameter tuning in deep learning models is inefficient and requires expertise.
method Introduces lower bounds to the linearized Laplace approximation of the marginal likelihood using neural tangent kernels.
result Optimization of hyperparameters can be significantly accelerated using the method.
Proposes a new metric selection for VM-PG with improved convergence.
problem Improves convergence of VM-PG methods for ill-conditioned problems.
method Diagonal Barzilai-Borwein stepsize for adaptive metric selection.
result Improved convergence results for ill-conditioned problems.
SkMM selects data for finetuning by balancing bias and variance.
problem Balancing bias and variance in high-dimensional finetuning.
method Gradient sketching for bias reduction and moment matching for variance reduction.
result Gradient sketching selects samples efficiently and accurately.
Greedy PIG adapts integrated gradients for better feature attribution.
problem Interpreting deep learning model predictions.
method Unified discrete optimization framework for feature attribution and selection.
result Greedy PIG improves feature attribution on various tasks.
Transformers excel at sparse token selection, surpassing FCNs in both worst and average cases.
problem Sparse token selection task
method One-layer transformer trained with gradient descent
result Transformers learn sparse token selection and exhibit strong out-of-distribution length generalization
EoS selectively shapes learning, affecting some groups more than others.
problem EoS affects learning differently across the data distribution.
method Branching intervention to enter or exit EoS regime, controlled perturbation to isolate mechanisms.
result EoS redistributes learning, amplifying progress on some groups and suppressing others.
Active Federated Learning selects clients to maximize efficiency.
problem Minimizing bandwidth usage and maximizing model accuracy in federated learning.
method Clients are selected with a probability conditioned on the current model and client data to maximize efficiency.
result Reduces the number of required training iterations by 20-70% while maintaining the same model accuracy.
A neural network approach for feature selection using mutual information.
problem Feature ranking and selection leading to sub-optimal solutions for class separability.
method Stochastic mutual information gradient estimation for dimensionality reduction.
result The network projects features onto an output space maximizing mutual information with class labels.
The paper examines how to protect LASSO-based feature selection from adversarial attacks.
problem Adversarial attacks on LASSO-based feature selection.
method Formulated as a bi-level optimization problem, reformulated LASSO with linear inequality constraints, solved using interior-point method, and modified using projected gradient descent.
result Demonstrated the effectiveness of the proposed method in protecting LASSO-based feature selection from adversarial attacks.
We propose a framework to perform streaming covariance selection. Our approach employs regularization constraints where a time-varying sparsity parameter is iteratively estimated via stochastic gradient descent. This allows for the regularization parameter to be efficiently learnt in an online manner. The proposed fram…
Classical stochastic gradient methods for optimization rely on noisy gradient approximations that become progressively less accurate as iterates approach a solution. The large noise and small signal in the resulting gradients makes it difficult to use them for adaptive stepsize selection and automatic stopping. We prop…
Selective-Backprop accelerates deep learning by focusing on high-loss examples.
problem Training deep neural networks is computationally expensive.
method Prioritizes examples with high loss for gradient computation, skipping others.
result Accelerates training up to 3.5x faster than standard SGD.
AES improves policy gradient performance by adaptively selecting experience.
problem High variance in gradient estimators from past trajectories.
method AES learns an adaptive sampling distribution to minimise gradient variance.
result AES leads to significantly improved performance in continuous control tasks.
Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization methods in training deep networks, it shows a slow convergence rate due to the larg…
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…
SDORE uses neural networks to estimate regression functions and their gradients, even with limited labeled data.
problem Nonparametric estimation of regression functions and their gradients.
method Semi-supervised deep ReQU neural networks with gradient norm regularization.
result Achieves minimax optimal convergence rates in L2-norm and plug-in gradient estimator convergence. New method selects data for labeling in RKHS to improve regression accuracy.
problem Labeling cost in supervised learning.
method Importance labeling scheme in RKHS with gradient descent.
result Gradient descent with proposed labeling scheme achieves optimal convergence rate.
Paper uses 2-step Gradient Boosting to predict VAT tax gap.
problem Estimating tax evasion and revenue loss from tax avoidance.
method 2-steps Gradient Boosting model to correct selection bias.
result Significantly improved prediction of VAT tax gap.
Greedy selection finds smaller, more accurate subnetworks.
problem Finding smaller, accurate subnetworks in large neural networks.
method Greedy forward selection starting from an empty network.
result Theoretical guarantee of finding subnetworks with lower loss.
Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today. We introduce a mini-batch selection strategy based on submodular function maximization. Our novel submodular formulation captures the informativeness of each sample and diversity of the whole subset. W…
Bayesian approach optimizes in-context learning for state space models.
problem Optimizing in-context learning for state space models.
method Bayesian optimal sequential prediction over latent sequence tasks.
result Bayesian optimal predictor converges to posterior predictive mean.
A new method for online personalized learning reduces gradient variance by dynamically selecting peers.
problem Online personalized decentralized learning with statistically heterogeneous clients.
method Gradient-based collaboration criterion allowing clients to dynamically select peers with similar gradients.
result The method acts as a variance reduction method, achieving optimal performance in certain conditions.
FedSel uses local differential privacy to protect data privacy in federated SGD.
problem Privacy leakage from gradients in federated SGD.
method Two-stage framework with top-k dimension selection and gradient accumulation.
result FedSel reduces privacy leakage by privately selecting important dimensions.
Gradient-trained embeddings select important tokens in text.
problem Understanding the theoretical structure of token embeddings.
method One-layer softmax attention model with gradient descent.
result Gradient-trained embeddings align with important tokens based on frequency.
AutoGD automatically adjusts learning rates for gradient descent.
problem Optimizing learning rates for gradient descent methods.
method AutoGD automatically adjusts learning rates based on iteration.
result AutoGD can recover the optimal rate of GD for a broad class of functions.
SIC measures dependency between variables, promoting feature selection.
problem Measuring and selecting features in high-dimensional data.
method Gradient regularized Integral Probability Metric (IPM) with sparsity inducing penalties.
result SIC can be used for reliable and interpretable feature selection.
Algorithm selects public datasets for private machine learning.
problem Choosing the most suitable public dataset for private machine learning.
method Measures gradient subspace distance between public and private datasets.
result Excess risk scales with the subspace distance between gradients.
Unified framework for gradient estimation in combinatorial spaces.
problem Scaling relaxed gradient estimators to large combinatorial distributions.
method Introducing stochastic softmax tricks within the perturbation model framework.
result Stochastic softmax tricks improve model performance and discover more latent structure.
In this note we discuss estimates for the curvature of 4-dimensional gradient Ricci soliton singularity models by applying Perelman's point selection, a fundamental result of Cheeger and Naber, and topological lemmas.
Here, we study different update rules in stochastic gradient descent (SGD) for online forecasting problems. The selection of the learning rate parameter is critical in SGD. However, it may not be feasible to tune this parameter in online learning. Therefore, it is necessary to have an update rule that is not sensitive …
Paper optimizes sparse feature selection for cancer detection using GSVP and SVM.
problem Sparse feature selection for cancer detection.
method Regularized GSVP with proximal gradient descent, feature selection via SVM.
result Near-perfect balanced accuracy with few selected features.
Laplace kernel feature selection offers statistical guarantees for nonparametric models with few samples.
problem Statistical guarantees for kernel-based feature selection in nonconvex optimization problems.
method Sharp characterization of the gradient of the objective function for Laplace kernel feature selection.
result Model-selection consistency for Laplace kernel-based feature selection in nonparametric settings with n∼logp samples.