Extends gradient-based optimization to spline functions.
problem Limitations of standard differentiable programming methods.
method Derives Jacobian of spline functions and uses it in predictive models.
result Improved performance in various applications.
Gradient-based methods improve understanding of deep learning survival models.
problem Limited interpretability of deep learning survival models hinders their adoption.
method Gradient-based explanation methods tailored to survival neural networks.
result Gradient-based methods capture feature effects and temporal dynamics.
A novel gradient-based method optimizes decision trees for complex tasks.
problem Training decision trees with arbitrary differentiable loss functions.
method Gradient-based optimization using first and second derivatives of loss functions.
result Improves accuracy and flexibility in decision tree optimization.
We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models even in offline settings. Hence, gradient based definition of regrets are common f…
We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly ext…
New method preserves convergence rates in gradient-based optimization.
problem How to discretize gradient-based optimization systems while preserving stability and convergence rates.
method Geometric framework for dissipative symplectic integration.
result Dissipative symplectic integrators preserve rates of convergence up to a controlled error.
New method creates universal perturbations to fool neural network interpretations.
problem Vulnerability of gradient-based saliency maps to adversarial perturbations.
method Gradient-based optimization and PCA-based approach to create UPI.
result Existence and successful application of Universal Perturbation for Interpretation (UPI).
In modern data analysis, random sampling is an efficient and widely-used strategy to overcome the computational difficulties brought by large sample size. In previous studies, researchers conducted random sampling which is according to the input data but independent on the response variable, however the response variab…
Meta learning works well with overparameterized models, a phenomenon called 'benign overfitting'.
problem Understanding why overparameterized models perform well in few-shot learning.
method Analyzed the generalization performance of gradient-based meta learning with an overparameterized meta linear regression model.
result Demonstrated that overparameterized meta learning can still generalize well, a phenomenon called 'benign overfitting'.
Background: It is still an open research area to theoretically understand why Deep Neural Networks (DNNs)---equipped with many more parameters than training data and trained by (stochastic) gradient-based methods---often achieve remarkably low generalization error. Contribution: We study DNN training by Fourier analysi…
Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these …
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.
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) with high probability. The paper tackles learning from imperfect human feedback, especially in dueling bandit problems.
problem Learning from human feedback that can be irrational or imperfect.
method Developed a Robustified Stochastic Mirror Descent for Imperfect Dueling (RoSMID) algorithm.
result Achieved nearly optimal regret for dueling bandit problems under imperfect human feedback.
Optimizes MMD learning for generative models with theoretical guarantees.
problem Theoretical guarantees for optimizing non-convex MMD objectives.
method Analyzes MMD optimization landscape for specific distributions.
result Gradient-based methods globally minimize MMD objective for certain distributions.
A new method reduces both input and output dimensions for better goal-oriented analysis.
problem Simultaneous reduction of input and output dimensions for more accurate analysis.
method Coupled input-output dimension reduction, optimizing gradient-based bounds.
result Determine most informative sensors and influential parameters efficiently.
Transformer-based method for causal discovery with prior knowledge integration.
problem Complex nonlinear dependencies and spurious correlations in time series data.
method Multi-layer Transformer forecaster with gradient-based causal structure extraction and attention masking for prior knowledge integration.
result Significant improvement in causal discovery and causal lag estimation compared to state-of-the-art methods.
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.
The paper explains how language models acquire complex skills through scaling laws and statistical analysis.
problem Understanding how language models acquire new skills as their size and training data increase.
method Statistical framework and mathematical analysis of scaling laws.
result Language models can learn complex skills efficiently due to a strong inductive bias.
Paper extends KPCA using dualization for faster, more robust algorithms.
problem Efficiently perform KPCA with robustness and sparsity.
method Dualization of convex functions for multiple objective functions, promoting sparsity and robustness.
result Significant speedup in KPCA training time and improved robustness and sparsity.
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differen…
Gradient-based methods for games suffer from discrete update steps that cause drift, affecting performance.
problem Gradient-based methods for two-player games suffer from drift due to discrete update steps.
method Derived modified continuous dynamical systems to closely follow the discrete dynamics of games.
result Identified distinct components of discretization drift that can alter or destabilize game performance.
Novel PCA method for high-dimensional inverse problems.
problem Optimizing large-scale random fields with gradient information.
method Gradient-Sensitive Principal Component Analysis (Gradient-SPCA) that modifies PCA using objective function gradients.
result Improvements in encoding quality for objective function minimization and field distribution.
Unified analysis of stochastic ADMM variants via SME.
problem Analyzing and optimizing stochastic ADMM variants for machine learning.
method Unified mathematical framework of SME for continuous-time analysis.
result Dynamics of stochastic ADMM approximated by SDEs with small noise.
Introduces new gradient-based methods for machine learning problems.
problem New challenges in machine learning due to decision-making and multi-agent problems.
method Gradient-based optimization and variational inequalities.
result Shifts focus from pattern recognition to decision-making and multi-agent problems.
Representational Similarity Analysis (RSA) aims to explore similarities between neural activities of different stimuli. Classical RSA techniques employ the inverse of the covariance matrix to explore a linear model between the neural activities and task events. However, calculating the inverse of a large-scale covarian…
The staircase property aids deep learning by guiding hierarchical feature learning.
problem Understanding how hierarchical structure influences deep learning performance.
method Defined and proved the staircase property for Boolean hypercube functions, and showed its learnability by layerwise stochastic coordinate descent.
result Staircase functions can be learned in polynomial time using layerwise stochastic coordinate descent on regular neural networks.
Meta learning improves with contextualizers that adapt to examples.
problem Few shot classification with limited labeled data.
method Implement contextualizers as generalizable prototypes for gradient-based meta learning.
result Contextualizers significantly boost performance on various few shot learning datasets.
Proposes VSGD optimizer combining probabilistic and gradient-based methods.
problem Uncertainty modeling in deep neural networks.
method Combines probabilistic and gradient-based approaches using SVI.
result VSGD outperforms Adam and SGD on image classification tasks.
We propose a technique for increasing the efficiency of gradient-based inference and learning in Bayesian networks with multiple layers of continuous latent vari- ables. We show that, in many cases, it is possible to express such models in an auxiliary form, where continuous latent variables are conditionally determini…
Gradient-based methods can be biased by distributional asymmetries in bivariate categorical data.
problem Gradient-based causal discovery methods can be biased by distributional asymmetries in bivariate categorical data.
method Identified and examined two distributional biases: Marginal Distribution Asymmetry and Marginal Distribution Shift Asymmetry. Employed two simple models to demonstrate and control these biases.
result Gradient-based methods can be biased by distributional asymmetries, and these biases can be controlled.
Federated learning improves SPCA for sparse components.
problem Data privacy and sharing constraints in machine learning.
method Federated learning framework applied to SPCA with L1 regularization and smoothing.
result Federated SPCA achieves sparse component loadings with improved interpretability.
This paper bounds the Lipschitz constants of neural networks and their gradients.
problem Estimating the Lipschitz constant of complex models like neural networks.
method Local upper and lower bounds on Lipschitz constants computed with respect to network parameters.
result It is impossible to derive global upper bounds for the Lipschitz constants of neural networks.
This paper analyzes deep and wide transformer training dynamics.
problem Understanding the training dynamics of infinitely deep and wide transformers.
method Develops a mean-field framework for gradient-based training of transformers, controlling a neural PDE.
result Establishes a rigorous foundation for gradient-based transformer training, proving convergence to global minima.
Gradient-based MCMC for discrete spaces improves sampling performance.
problem Sampling in discrete spaces using traditional methods is challenging.
method Introduced new discrete Metropolis-Hastings samplers inspired by MALA, with a novel preconditioning technique.
result Demonstrated strong empirical performance across various challenging sampling problems.
Neural networks can achieve optimal sample complexity for learning single-index models.
problem Achieving optimal computational-statistical tradeoff in learning Gaussian single-index models.
method Unified gradient-based algorithm for training a two-layer neural network, adaptable to various loss and activation functions.
result Sample complexity of ds⋆/2∨d matches the SQ lower bound up to a polylogarithmic factor. Generalization in deep neural networks can be analyzed using minimax rates for gradient methods.
problem Generalization performance of over-parameterized neural networks
method Establishing a connection between gradient-based methods and kernel methods
result Deriving minimax-optimal rates for GD and SGD under polynomial network width scaling
LocalKMeans parallelizes Lloyd's algorithm for distributed data.
problem Efficiently clustering data across multiple machines.
method Parallel local iterations with synchronization every L steps.
result Higher required signal-to-noise ratio due to local steps.
Proves equations for high-dimensional gradient-based methods from Gaussian data.
problem High-dimensional asymptotics of gradient-based learning algorithms.
method Closed-form equations derived from dynamical mean-field theory.
result Equations match those from discretized DMFT for gradient flow.
New algorithm guarantees performance on noisy data.
problem Learning with noisy data and heavy-tailed distributions.
method Anytime online-to-batch conversion for smooth objectives.
result Stochastic gradient-based algorithm with sub-Gaussian error bounds.
We present a very fast algorithm for general matrix factorization of a data matrix for use in the statistical analysis of high-dimensional data via latent factors. Such data are prevalent across many application areas and generate an ever-increasing demand for methods of dimension reduction in order to undertake the st…
Gradient-based adversarial attacks on neural networks can be crafted in a variety of ways by varying either how the attack algorithm relies on the gradient, the network architecture used for crafting the attack, or both. Most recent work has focused on defending classifiers in a case where there is no uncertainty about…
DAIS improves AIS for differentiable marginal likelihood estimation.
problem Differentiable marginal likelihood estimation for complex models.
method Proposes Differentiable Annealed Importance Sampling (DAIS) to make AIS differentiable.
result DAIS achieves convergence and consistency in Bayesian linear regression.
SAP learns efficient task-specific parameter subspaces for few-shot learning.
problem Efficient few-shot learning with limited data.
method Subspace Adaptation Prior (SAP) learns task-specific parameter subspaces for efficient few-shot learning.
result SAP yields superior or competitive performance in few-shot image classification.
Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new approach has transformed the combinatorial structure learning problem into a continuous one and then solv…
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specifically in the case of meta-reinforcement learning (meta-RL), we can show that gradient-based meta-learners are sensitive to task distributions…
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, the problem remains open. In this paper, we analyse the geometry of adversarial attacks in the large-data, overparametrized …
In the recent years, Riemannian shape analysis of curves and surfaces has found several applications in medical image analysis. In this paper we present a numerical discretization of second order Sobolev metrics on the space of regular curves in Euclidean space. This class of metrics has several desirable mathematical …