اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدRapidly Adapting Moment Estimation
113
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates. Differently from existing methods, we make use of the most recent first moment of gradients to compute the individual learning rates per iteration. The motivation behind it is that the dynamic variation of the first moment of gradients may provide useful information to obtain the learning rates. We refer to the new method as the rapidly adapting moment estimation (RAME). The theoretical convergence of deterministic RAME is studied by using an analysis similar to the one used in [1] for Adam. Experimental results for training a number of DNNs show promising performance of RAME w.r.t. the convergence speed and generalization performance compared to the stochastic heavy-ball (SHB) method, Adam, and RMSprop.
قيم البحث
اقرأ أيضاً
Uncertainty quantification for deep neural networks has recently evolved through many techniques. In this work, we revisit Laplace approximation, a classical approach for posterior approximation that is computationally attractive. However, instead of
computing the curvature matrix, we show that, under some regularity conditions, the Laplace approximation can be easily constructed using the gradient second moment. This quantity is already estimated by many exponential moving average variants of Adagrad such as Adam and RMSprop, but is traditionally discarded after training. We show that our method (L2M) does not require changes in models or optimization, can be implemented in a few lines of code to yield reasonable results, and it does not require any extra computational steps besides what is already being computed by optimizers, without introducing any new hyperparameter. We hope our method can open new research directions on using quantities already computed by optimizers for uncertainty estimation in deep neural networks.
A major research direction in contextual bandits is to develop algorithms that are computationally efficient, yet support flexible, general-purpose function approximation. Algorithms based on modeling rewards have shown strong empirical performance,
but typically require a well-specified model, and can fail when this assumption does not hold. Can we design algorithms that are efficient and flexible, yet degrade gracefully in the face of model misspecification? We introduce a new family of oracle-efficient algorithms for $varepsilon$-misspecified contextual bandits that adapt to unknown model misspecification -- both for finite and infinite action settings. Given access to an online oracle for square loss regression, our algorithm attains optimal regret and -- in particular -- optimal dependence on the misspecification level, with no prior knowledge. Specializing to linear contextual bandits with infinite actions in $d$ dimensions, we obtain the first algorithm that achieves the optimal $O(dsqrt{T} + varepsilonsqrt{d}T)$ regret bound for unknown misspecification level $varepsilon$. On a conceptual level, our results are enabled by a new optimization-based perspective on the regression oracle reduction framework of Foster and Rakhlin, which we anticipate will find broader use.
Probability Density Estimation (PDE) is a multivariate discrimination technique based on sampling signal and background densities defined by event samples from data or Monte-Carlo (MC) simulations in a multi-dimensional phase space. In this paper, we
present a modification of the PDE method that uses a self-adapting binning method to divide the multi-dimensional phase space in a finite number of hyper-rectangles (cells). The binning algorithm adjusts the size and position of a predefined number of cells inside the multi-dimensional phase space, minimising the variance of the signal and background densities inside the cells. The implementation of the binning algorithm PDE-Foam is based on the MC event-generation package Foam. We present performance results for representative examples (toy models) and discuss the dependence of the obtained results on the choice of parameters. The new PDE-Foam shows improved classification capability for small training samples and reduced classification time compared to the original PDE method based on range searching.
Rapid performance recovery from unforeseen environmental perturbations remains a grand challenge in swarm robotics. To solve this challenge, we investigate a behaviour adaptation approach, where one searches an archive of controllers for potential re
covery solutions. To apply behaviour adaptation in swarm robotic systems, we propose two algorithms: (i) Swarm Map-based Optimisation (SMBO), which selects and evaluates one controller at a time, for a homogeneous swarm, in a centralised fashion; and (ii) Swarm Map-based Optimisation Decentralised (SMBO-Dec), which performs an asynchronous batch-based Bayesian optimisation to simultaneously explore different controllers for groups of robots in the swarm. We set up foraging experiments with a variety of disturbances: injected faults to proximity sensors, ground sensors, and the actuators of individual robots, with 100 unique combinations for each type. We also investigate disturbances in the operating environment of the swarm, where the swarm has to adapt to drastic changes in the number of resources available in the environment, and to one of the robots behaving disruptively towards the rest of the swarm, with 30 unique conditions for each such perturbation. The viability of SMBO and SMBO-Dec is demonstrated, comparing favourably to variants of random search and gradient descent, and various ablations, and improving performance up to 80% compared to the performance at the time of fault injection within at most 30 evaluations.
Density ratio estimation serves as an important technique in the unsupervised machine learning toolbox. However, such ratios are difficult to estimate for complex, high-dimensional data, particularly when the densities of interest are sufficiently di
fferent. In our work, we propose to leverage an invertible generative model to map the two distributions into a common feature space prior to estimation. This featurization brings the densities closer together in latent space, sidestepping pathological scenarios where the learned density ratios in input space can be arbitrarily inaccurate. At the same time, the invertibility of our feature map guarantees that the ratios computed in feature space are equivalent to those in input space. Empirically, we demonstrate the efficacy of our approach in a variety of downstream tasks that require access to accurate density ratios such as mutual information estimation, targeted sampling in deep generative models, and classification with data augmentation.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
