Search Results for author:
Found 54 papers, 21 papers with code
Enhancing Policy Gradient with the Polyak Step-Size Adaption
Policy gradient is a widely utilized and foundational algorithm in the field of reinforcement learning (RL).
Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation
This improvement is comparable to a square-root of the condition number in the worst case and address criticism that guarantees for stochastic acceleration could be worse than those for SGD.
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
We show that the heavy-tailed class imbalance found in language modeling tasks leads to difficulties in the optimization dynamics.
Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm
We show that bound- and summation-constrained steepest descent in the L1-norm guarantees more progress per iteration than previous rules and can be computed in only $O(n \log n)$ time.
Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be
This suggests that Adam outperform SGD because it uses a more robust gradient estimate.
Fast Convergence of Random Reshuffling under Over-Parameterization and the Polyak-Łojasiewicz Condition
Modern machine learning models are often over-parameterized and as a result they can interpolate the training data.
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
Riemannian submanifold optimization with momentum is computationally challenging because, to ensure that the iterates remain on the submanifold, we often need to solve difficult differential equations.
Target-based Surrogates for Stochastic Optimization
Our target optimization framework uses the (expensive) gradient computation to construct surrogate functions in a \emph{target space} (e. g. the logits output by a linear model for classification) that can be minimized efficiently.
Improved Policy Optimization for Online Imitation Learning
Specifically, if the class of policies is sufficiently expressive to contain the expert policy, we prove that DAGGER achieves constant regret.
Structured second-order methods via natural gradient descent
In this paper, we propose new structured second-order methods and structured adaptive-gradient methods obtained by performing natural-gradient descent on structured parameter spaces.
SVRG Meets AdaGrad: Painless Variance Reduction
Variance reduction (VR) methods for finite-sum minimization typically require the knowledge of problem-dependent constants that are often unknown and difficult to estimate.
Tractable structured natural gradient descent using local parameterizations
Natural-gradient descent (NGD) on structured parameter spaces (e. g., low-rank covariances) is computationally challenging due to difficult Fisher-matrix computations.
The pathway elaboration method for mean first passage time estimation in large continuous-time Markov chains with applications to nucleic acid kinetics
We then compare the performance of pathway elaboration with the stochastic simulation algorithm (SSA) for MFPT estimation on 237 of the reactions for which SSA is feasible.
Robust Asymmetric Learning in POMDPs
Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes.
Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent
In this work we first show that for the common setting of exponential family distributions, viewing EM as a mirror descent algorithm leads to convergence rates in Kullback-Leibler (KL) divergence.
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses
We extend the known regret bounds for classical OCO algorithms to the relative setting.
Variance-Reduced Methods for Machine Learning
Stochastic optimization lies at the heart of machine learning, and its cornerstone is stochastic gradient descent (SGD), a method introduced over 60 years ago.
Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search)
Under an interpolation assumption, we prove that AMSGrad with a constant step-size and momentum can converge to the minimizer at the faster $O(1/T)$ rate for smooth, convex functions.
Adaptive Gradient Methods Converge Faster with Over-Parameterization (but you should do a line-search)
In this setting, we prove that AMSGrad with constant step-size and momentum converges to the minimizer at a faster $O(1/T)$ rate.
Handling the Positive-Definite Constraint in the Bayesian Learning Rule
The Bayesian learning rule is a natural-gradient variational inference method, which not only contains many existing learning algorithms as special cases but also enables the design of new algorithms.
Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures
Our generalization enables us to establish a connection between Stein's lemma and the reparamterization trick to derive gradients of expectations of a large class of functions under weak assumptions.
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
Under this condition, we show that the regularized subsampled Newton method (R-SSN) achieves global linear convergence with an adaptive step-size and a constant batch-size.
xRAC: Execution and Access Control for Restricted Application Containers on Managed Hosts
If the user is permitted to use the RAC on a managed host, launching the RAC is authorized and access to protected network resources may be given, e. g., to internal networks, servers, or the Internet.
Networking and Internet Architecture Cryptography and Security
Where are the Masks: Instance Segmentation with Image-level Supervision
A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective.
Ranked #7 on
Image-level Supervised Instance Segmentation
on PASCAL VOC 2012 val
(using extra training data)
Image-level Supervised Instance Segmentation
Semantic Segmentation
Instance Segmentation with Point Supervision
Instance segmentation methods often require costly per-pixel labels.
Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
Natural-gradient methods enable fast and simple algorithms for variational inference, but due to computational difficulties, their use is mostly limited to \emph{minimal} exponential-family (EF) approximations.
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
To improve the proposed methods' practical performance, we give heuristics to use larger step-sizes and acceleration.
Efficient Deep Gaussian Process Models for Variable-Sized Input
The key advantage is that the combination of GP and DRF leads to a tractable model that can both handle a variable-sized input as well as learn deep long-range dependency structures of the data.
Distributed Maximization of Submodular plus Diversity Functions for Multi-label Feature Selection on Huge Datasets
In this paper, we consider this problem as an optimization problem that seeks to maximize the sum of a sum-sum diversity function and a non-negative monotone submodular function.
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
Uncertainty estimation in large deep-learning models is a computationally challenging task, where it is difficult to form even a Gaussian approximation to the posterior distribution.
Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron
Under this condition, we prove that constant step-size stochastic gradient descent (SGD) with Nesterov acceleration matches the convergence rate of the deterministic accelerated method for both convex and strongly-convex functions.
Combining Bayesian Optimization and Lipschitz Optimization
Indeed, in a particular setting, we prove that using the Lipschitz information yields the same or a better bound on the regret compared to using Bayesian optimization on its own.
A Less Biased Evaluation of Out-of-distribution Sample Detectors
What makes this problem different from a typical supervised learning setting is that the distribution of outliers used in training may not be the same as the distribution of outliers encountered in the application.
Where are the Blobs: Counting by Localization with Point Supervision
However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods.
Ranked #1 on
Object Counting
on Pascal VOC 2007 count-test
New Insights into Bootstrapping for Bandits
We investigate the use of bootstrapping in the bandit setting.
Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence
Block coordinate descent (BCD) methods are widely used for large-scale numerical optimization because of their cheap iteration costs, low memory requirements, amenability to parallelization, and ability to exploit problem structure.
Optimization and Control 90C06
Online Learning Rate Adaptation with Hypergradient Descent
We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice.
Horde of Bandits using Gaussian Markov Random Fields
The gang of bandits (GOB) model \cite{cesa2013gang} is a recent contextual bandits framework that shares information between a set of bandit problems, related by a known (possibly noisy) graph.
Model-Independent Online Learning for Influence Maximization
We consider influence maximization (IM) in social networks, which is the problem of maximizing the number of users that become aware of a product by selecting a set of "seed" users to expose the product to.
Fast Patch-based Style Transfer of Arbitrary Style
This results in a procedure for artistic style transfer that is efficient but also allows arbitrary content and style images.
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition
In 1963, Polyak proposed a simple condition that is sufficient to show a global linear convergence rate for gradient descent.
Play and Learn: Using Video Games to Train Computer Vision Models
We present experiments assessing the effectiveness on real-world data of systems trained on synthetic RGB images that are extracted from a video game.
StopWasting My Gradients: Practical SVRG
We present and analyze several strategies for improving the performance ofstochastic variance-reduced gradient (SVRG) methods.
Stop Wasting My Gradients: Practical SVRG
We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods.
Faster Stochastic Variational Inference using Proximal-Gradient Methods with General Divergence Functions
We also give a convergence-rate analysis of our method and many other previous methods which exploit the geometry of the space.
Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection
There has been significant recent work on the theory and application of randomized coordinate descent algorithms, beginning with the work of Nesterov [SIAM J.
Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields
We apply stochastic average gradient (SAG) algorithms for training conditional random fields (CRFs).
Influence Maximization with Bandits
We consider the problem of \emph{influence maximization}, the problem of maximizing the number of people that become aware of a product by finding the `best' set of `seed' users to expose the product to.
Hierarchical Maximum-Margin Clustering
We present a hierarchical maximum-margin clustering method for unsupervised data analysis.
Convex Optimization for Big Data
This article reviews recent advances in convex optimization algorithms for Big Data, which aim to reduce the computational, storage, and communications bottlenecks.
Minimizing Finite Sums with the Stochastic Average Gradient
Further, in many cases the convergence rate of the new method is also faster than black-box deterministic gradient methods, in terms of the number of gradient evaluations.
A Stochastic Gradient Method with an Exponential Convergence _Rate for Finite Training Sets
We propose a new stochastic gradient method for optimizing the sum of a finite set of smooth functions, where the sum is strongly convex.
Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
We consider the problem of optimizing the sum of a smooth convex function and a non-smooth convex function using proximal-gradient methods, where an error is present in the calculation of the gradient of the smooth term or in the proximity operator with respect to the second term.
An interior-point stochastic approximation method and an L1-regularized delta rule
The stochastic approximation method is behind the solution to many important, actively-studied problems in machine learning.
