This work shows synthetic gradients can outperform backpropagation in sample efficiency.
problem The efficiency of backpropagation in training neural networks.
method Unified vectorized feedback framework for loss-based and reward-based learning, introducing synthetic gradients.
result Synthetic gradients can achieve lower gradient-estimation mean squared error than backpropagation under certain conditions.
Meta-learning framework improves model performance on few-shot classification tasks.
problem Improving model performance on few-shot classification tasks.
method Empirical Bayes formulation with synthetic gradients for transductive meta-learning.
result Meta-learning framework outperforms previous state-of-the-art methods on benchmarks.
Develops a method to control model behavior with synthetic data.
problem Controlling language model behavior via synthetic training data.
method Dataset Policy Gradient (DPG) to optimize synthetic data generators.
result Can cause target models to embed specific patterns or rephrase inputs.
Synthetic data helps prevent forgetting when learning sequentially.
problem Catastrophic forgetting in neural networks.
method Generate synthetic data via two-step optimisation process using meta-gradients.
result Training on synthetic data prevents forgetting when learning sequentially.
New methods distill data for deep networks efficiently.
problem Reduction of training data cost and inconvenience.
method Generative teaching networks, gradient matching, Implicit Function Theorem.
result New methods are computationally more efficient and improve model performance.
Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation pipeline requires numerous design decisions such as the selection of 3D shapes and …
Paper proposes a new method to detect convergence in SGD.
problem Detecting the transition from fast progress to oscillation in SGD.
method Analyzes Pflug's test and proposes a novel statistical procedure.
result The novel procedure accurately detects stationarity in SGD.
DPDMs use DP-SGD to generate private synthetic data.
problem Generating private synthetic data from sensitive datasets.
method Introduced DP-SGD for DMs, investigated DM parameterization and sampling, proposed noise multiplicity.
result Achieved state-of-the-art performance in image generation benchmarks.
AutoSimulate efficiently optimizes synthetic data generation.
problem Optimizing synthetic data generation for machine learning.
method Differentiable approximation of the objective function for efficient optimization.
result Significantly faster (up to 50x) and more efficient (up to 30x) synthetic data generation.
Paper proposes HCDC to improve hyperparameter search efficiency.
problem Poor generalizability of dataset condensation across different hyperparameters.
method HCDC algorithm that matches hyperparameter gradients for synthetic validation dataset.
result HCDC effectively maintains validation-performance rankings of models.
New defense method protects client data privacy in federated learning.
problem Gradient leakage attacks in federated learning.
method Learning to obscure data to generate synthetic samples.
result Synthetic samples preserve predictive features and protect privacy.
Analyzes factors affecting flow VI performance.
problem Consistent performance of flow VI across studies.
method Step-by-step analysis of capacity, objectives, batchsize, estimators, and step-sizes.
result Specific recommendations and a flow VI recipe.
MAZE attacks a model without data, using synthetic inputs.
problem Model Stealing attacks that require data to replicate a target model.
method MAZE uses zeroth-order gradient estimation to create synthetic inputs.
result MAZE achieves high clone accuracy without data.
This paper presents a new class of gradient methods for distributed machine learning that adaptively skip the gradient calculations to learn with reduced communication and computation. Simple rules are designed to detect slowly-varying gradients and, therefore, trigger the reuse of outdated gradients. The resultant gra…
Gradient tree boosting is a prediction algorithm that sequentially produces a model in the form of linear combinations of decision trees, by solving an infinite-dimensional optimization problem. We combine gradient boosting and Nesterov's accelerated descent to design a new algorithm, which we call AGB (for Accelerated…
Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent ba…
Synthetic data replaces model updates in federated learning.
problem High computational costs in transmitting model parameters.
method Transmitting synthetic data instead of model updates.
result Reduces communication costs by more than an order of magnitude.
Gradient boosting with randomized trees reduces discontinuities and complexity.
problem Discontinuities in regression functions due to sparse training data.
method Gradient boosting machine with partially randomized decision trees.
result Improves robustness and computational efficiency of gradient boosting.
We observe that gradients computed via the reparameterization trick are in direct correspondence with solutions of the transport equation in the formalism of optimal transport. We use this perspective to compute (approximate) pathwise gradients for probability distributions not directly amenable to the reparameterizati…
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits,…
This paper studies the performance of a recently proposed preconditioned stochastic gradient descent (PSGD) algorithm on recurrent neural network (RNN) training. PSGD adaptively estimates a preconditioner to accelerate gradient descent, and is designed to be simple, general and easy to use, as stochastic gradient desce…
A key challenge for gradient based optimization methods in model-free reinforcement learning is to develop an approach that is sample efficient and has low variance. In this work, we apply Kronecker-factored curvature estimation technique (KFAC) to a recently proposed gradient estimator for control variate optimization…
In this paper, we propose an implicit gradient descent algorithm for the classic k-means problem. The implicit gradient step or backward Euler is solved via stochastic fixed-point iteration, in which we randomly sample a mini-batch gradient in every iteration. It is the average of the fixed-point trajectory that is c…
We provide the first experimental results on non-synthetic datasets for the quasi-diagonal Riemannian gradient descents for neural networks introduced in [Ollivier, 2015]. These include the MNIST, SVHN, and FACE datasets as well as a previously unpublished electroencephalogram dataset. The quasi-diagonal Riemannian alg…
This work proposes a new method for variational inference using Wasserstein gradient descent.
problem Optimizing variational parameters to match a true posterior distribution.
method Reinterpreting VI as an optimization problem over a variational parameter space, using Wasserstein gradient descent.
result The proposed Wasserstein gradient descent can be seen as a generalization of existing optimization techniques in VI.
Improved bounds for proximal gradient algorithms with computational errors.
problem Analyzing convergence of proximal gradient algorithms with inaccuracies.
method Deriving new tighter deterministic and probabilistic bounds for convex composite problems.
result Probabilistic bounds are more robust and accurate for algorithm verification and performance guarantees.
We will study metric measure spaces (X,d,m) beyond the scope of spaces with synthetic lower Ricci bounds. In particular, we introduce distribution-valued lower Ricci bounds BE1(κ,∞) ∙ for which we prove the equivalence with sharp gradient estimates, ∙ the class of which will be preserved under…
Gradient-guided nested sampling improves posterior inference efficiency.
problem Efficiently sampling from complex posterior distributions.
method Gradient-guided nested sampling combining differentiable programming, Hamiltonian slice sampling, clustering, mode separation, dynamic nested sampling, and parallelization.
result Significantly faster mode discovery and more accurate partition function estimates.
New algorithm improves source separation with multi-trial supervision.
problem Non-convex optimization and interpretability of independent components.
method Proximal gradient-type algorithm in invertible matrices with backpropagation for joint learning.
result Increased success rate of non-convex optimization and improved interpretability.
In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this paper, we replace policy gradient with proximal policy optimization (…
AdaX improves Adam by exponentially accumulating past gradients, leading to better performance in machine learning tasks.
problem Adam's fast convergence can lead to local minimums in non-convex problems.
method AdaX exponentially accumulates past gradients to adaptively tune the learning rate.
result AdaX outperforms Adam in various machine learning tasks, including computer vision and natural language processing.
Gradient descent on normalized networks reveals sparsity preferences.
problem Understanding the inductive bias of gradient descent on normalized neural nets.
method Analysis of gradient descent on weight-normalized smooth homogeneous neural nets, focusing on SWN and EWN.
result EWN causes weights to be updated in a way that prefers asymptotic relative sparsity.
Stochastic gradient MCMC (SG-MCMC) has played an important role in large-scale Bayesian learning, with well-developed theoretical convergence properties. In such applications of SG-MCMC, it is becoming increasingly popular to employ distributed systems, where stochastic gradients are computed based on some outdated par…
Semiparametric method removes bias in functional bilevel gradient estimation.
problem First-order bias in plug-in hypergradient when lower-level problem is nonparametric.
method Semiparametric debiasing theory based on efficient influence function leads to cross-fitted orthogonal hypergradient estimator.
result Asymptotic normality and uniform control over outer parameter established for the estimator.
Proposes ridge regression on Riemannian manifolds for time-series prediction.
problem Time-series prediction on Riemannian manifolds.
method Combines Riemannian least-squares fitting via Bézier curves, empirical covariance on manifolds, and Mahalanobis distance regularization.
result Significant error reduction in synthetic spherical experiments and hurricane forecasting.
Sobolev training helps neural nets fit function values and derivatives.
problem Training neural nets to match function values and derivatives accurately.
method Using Sobolev loss with gradient flow for overparameterized networks.
result Gradient flow from random initialization can fit any function and its derivatives.
Deep learning for HJB PDEs using synthetic data and residual minimization.
problem Solving Hamilton-Jacobi-Bellman PDEs for optimal control problems.
method Gradient-augmented synthetic dataset for supervised learning, residual minimization.
result Improves accuracy and efficiency of deep learning for HJB PDEs.
This research tackles uncertainty in gradient boosting models using ensemble methods.
problem Quantifying uncertainty in gradient boosting models for high-risk applications.
method Probabilistic ensemble-based framework for gradient boosting classification and regression models.
result Ensembles of gradient boosting models detect anomalous inputs but have limited ability to improve total uncertainty.
Paper uses SGD for solving linear inverse problems, improving empirical performance.
problem Solving statistical inverse problems in science and engineering.
method Stochastic Gradient Descent (SGD) for linear inverse problems, with smoothing techniques.
result Consistency and finite sample bounds for excess risk demonstrated.
Differentially private method for synthetic data generation from vertically partitioned data.
problem Generating synthetic data from vertically partitioned data while preserving privacy.
method Differentially private stochastic gradient descent (DP-SGD) algorithm combined with secure multiparty computation (MPC).
result Comparable accuracy to non-partitioned data, demonstrating privacy-preserving synthetic data generation.
A new method for sampling high-dimensional distributions overcomes overfitting.
problem Overfitting in energy-based models during gradient descent.
method Mean-field microcanonical gradient descent, which samples multiple data points simultaneously.
result The method reduces entropy loss while maintaining likelihood fit, improving overfitting issues.
The paper shows averaging gradients leads to memorization, proposing an alternative algorithm to focus on invariances.
problem The principle that 'good explanations are hard to vary' in deep learning is investigated.
method Formalizing consistency for loss surface minima, proposing an alternative algorithm based on logical AND.
result The alternative algorithm prevents memorization and focuses on invariances.
A new method improves likelihood-free Bayesian inference by transforming summary statistics and using efficient Variational Bayes.
problem Incorrectly assuming normally distributed summary statistics in likelihood-free Bayesian inference.
method Wasserstein Gaussianization transformation combined with robust BSL and efficient Variational Bayes.
result Highly efficient and reliable approximate Bayesian inference for likelihood-free problems.
New method optimizes multiple objectives using particle dynamics and gradient flow.
problem Optimizing multiple conflicting objectives in complex scenarios.
method Interacting particle method combining Langevin and birth-death dynamics with a dominance potential.
result Method effectively relocates dominated particles, improving Pareto optimality.
We present a novel approach for fully non-stationary Gaussian process regression (GPR), where all three key parameters -- noise variance, signal variance and lengthscale -- can be simultaneously input-dependent. We develop gradient-based inference methods to learn the unknown function and the non-stationary model param…
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.
Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There exist many inexpensive data sources on the web, but they tend to contain inaccurate…
ScoreStop uses gradient tests to stop gradient boosting early.
problem Overfitting in gradient boosted decision trees.
method ScoreStop uses a functional score test based on gradients to stop boosting.
result ScoreStop is competitive with loss-based early stopping methods.