اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدL2M: Practical posterior Laplace approximation with optimization-driven second moment estimation
66
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
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.
قيم البحث
اقرأ أيضاً
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 o
f 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.
Ensembles of independently trained neural networks are a state-of-the-art approach to estimate predictive uncertainty in Deep Learning, and can be interpreted as an approximation of the posterior distribution via a mixture of delta functions. The tra
ining of ensembles relies on non-convexity of the loss landscape and random initialization of their individual members, making the resulting posterior approximation uncontrolled. This paper proposes a novel and principled method to tackle this limitation, minimizing an $f$-divergence between the true posterior and a kernel density estimator in a function space. We analyze this objective from a combinatorial point of view, and show that it is submodular with respect to mixture components for any $f$. Subsequently, we consider the problem of greedy ensemble construction, and from the marginal gain of the total objective, we derive a novel diversity term for ensemble methods. The performance of our approach is demonstrated on computer vision out-of-distribution benchmarks in a range of architectures trained on multiple datasets. The source code of our method is publicly available at https://github.com/MIPT-Oulu/greedy_ensembles_training.
In this paper, we address a variant of the marketing mix optimization (MMO) problem which is commonly encountered in many industries, e.g., retail and consumer packaged goods (CPG) industries. This problem requires the spend for each marketing activi
ty, if adjusted, be changed by a non-negligible degree (minimum change) and also the total number of activities with spend change be limited (maximum number of changes). With these two additional practical requirements, the original resource allocation problem is formulated as a mixed integer nonlinear program (MINLP). Given the size of a realistic problem in the industrial setting, the state-of-the-art integer programming solvers may not be able to solve the problem to optimality in a straightforward way within a reasonable amount of time. Hence, we propose a systematic reformulation to ease the computational burden. Computational tests show significant improvements in the solution process.
Due to the phenomenon of posterior collapse, current latent variable generative models pose a challenging design choice that either weakens the capacity of the decoder or requires augmenting the objective so it does not only maximize the likelihood o
f the data. In this paper, we propose an alternative that utilizes the most powerful generative models as decoders, whilst optimising the variational lower bound all while ensuring that the latent variables preserve and encode useful information. Our proposed $delta$-VAEs achieve this by constraining the variational family for the posterior to have a minimum distance to the prior. For sequential latent variable models, our approach resembles the classic representation learning approach of slow feature analysis. We demonstrate the efficacy of our approach at modeling text on LM1B and modeling images: learning representations, improving sample quality, and achieving state of the art log-likelihood on CIFAR-10 and ImageNet $32times 32$.
Heuristic algorithms such as simulated annealing, Concorde, and METIS are effective and widely used approaches to find solutions to combinatorial optimization problems. However, they are limited by the high sample complexity required to reach a reaso
nable solution from a cold-start. In this paper, we introduce a novel framework to generate better initial solutions for heuristic algorithms using reinforcement learning (RL), named RLHO. We augment the ability of heuristic algorithms to greedily improve upon an existing initial solution generated by RL, and demonstrate novel results where RL is able to leverage the performance of heuristics as a learning signal to generate better initialization. We apply this framework to Proximal Policy Optimization (PPO) and Simulated Annealing (SA). We conduct a series of experiments on the well-known NP-complete bin packing problem, and show that the RLHO method outperforms our baselines. We show that on the bin packing problem, RL can learn to help heuristics perform even better, allowing us to combine the best parts of both approaches.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
