论文检索

Reinforcement Learning

Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, Marcello Restelli

Policy evaluation via Monte Carlo (MC) simulation is at the core of many MC Reinforcement Learning (RL) algorithms (e.g., policy gradient methods). In this context, the designer of the learning system specifies an interaction budget that the agent usually spends by collecting trajectories of *fixed length* within a simulator. However, is this data collection strategy the best option? To answer this question, in this paper, we consider as quality index the variance of an unbiased policy return estimator that uses trajectories of different lengths, i.e., *truncated*. We first derive a closed-form expression of this variance that clearly shows the sub-optimality of the fixed-length trajectory schedule. Furthermore, it suggests that adaptive data collection strategies that spend the available budget sequentially might be able to allocate a larger portion of transitions in timesteps in which more accurate sampling is required to reduce the variance of the final estimate. Building on these findings, we present an *adaptive* algorithm called **R**obust and **I**terative **D**ata collection strategy **O**ptimization (RIDO). The main intuition behind RIDO is to split the available interaction budget into mini-batches. At each round, the agent determines the most convenient schedule of trajectories that minimizes an empirical and robust estimate of the estimator's variance. After discussing the theoretical properties of our method, we conclude by assessing its performance across multiple domains. Our results show that RIDO can adapt its trajectory schedule toward timesteps where more sampling is required to increase the quality of the final estimation.

Afra Amini, Li Du, Ryan Cotterell

Gradient-based sampling algorithms have demonstrated their effectiveness in text generation, especially in the context of controlled text generation. However, there exists a lack of theoretically grounded and principled approaches for this task. In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods. We use discrete distributions given by language models to define densities and develop an algorithm based on Hamiltonian Monte Carlo to sample from them. We name our gradient-based technique Structured Voronoi Sampling (SVS). In an experimental setup where the reference distribution is known, we show that the empirical distribution of SVS samples is closer to the reference distribution compared to alternative sampling schemes. Furthermore, in a controlled generation task, SVS is able to generate fluent and diverse samples while following the control targets significantly better than other methods.

Probabilistic Methods/Monte Carlo and Sampling Methods

Mohammad Reza Karimi Jaghargh, Ya-Ping Hsieh, Andreas Krause

Interacting particle systems have proven highly successful in various machinelearning tasks, including approximate Bayesian inference and neural network optimization. However, the analysis of thesesystems often relies on the simplifying assumption of the \emph{mean-field} limit, where particlenumbers approach infinity and infinitesimal step sizes are used. In practice, discrete time steps,finite particle numbers, and complex integration schemes are employed, creating a theoretical gapbetween continuous-time and discrete-time processes. In this paper, we present a novel frameworkthat establishes a precise connection between these discrete-time schemes and their correspondingmean-field limits in terms of convergence properties and asymptotic behavior. By adopting a dynamical system perspective, our framework seamlessly integrates various numerical schemes that are typically analyzed independently. For example, our framework provides a unified treatment of optimizing an infinite-width two-layer neural network and sampling via Stein Variational Gradient descent, which were previously studied in isolation.

Theory/Optimization

Syamantak Kumar, Purnamrita Sarkar

Since its inception in 1982, Oja's algorithm has become an established method for streaming principle component analysis (PCA). We study the problem of streaming PCA, where the data-points are sampled from an irreducible, aperiodic, and reversible Markov chain starting in stationarity. Our goal is to estimate the top eigenvector of the unknown covariance matrix of the stationary distribution. This setting has implications in scenarios where data can solely be sampled from a Markov Chain Monte Carlo (MCMC) type algorithm, and the objective is to perform inference on parameters of the stationary distribution. Most convergence guarantees for Oja's algorithm in the literature assume that the data-points are sampled IID. For data streams with Markovian dependence, one typically downsamples the data to get a "nearly" independent data stream. In this paper, we obtain the first near-optimal rate for Oja's algorithm on the entire data, where we remove the logarithmic dependence on the sample size, $n$, resulting from throwing data away in downsampling strategies.

Yanfu Zhang, Shangqian Gao, Heng Huang

Deep neural networks achieve great success in many visual recognition tasks. However, the model deployment is usually subject to some computational resources. Model pruning under computational budget has attracted growing attention. In this paper, we focus on the discrimination-aware compression of Convolutional Neural Networks (CNNs). In prior arts, directly searching the optimal sub-network is an integer programming problem, which is non-smooth, non-convex, and NP-hard. Meanwhile, the heuristic pruning criterion lacks clear interpretability and doesn't generalize well in applications. To address this problem, we formulate sub-networks as samples from a multivariate Bernoulli distribution and resort to the approximation of continuous problem. We propose a new flexible search scheme via alternating exploration and estimation. In the exploration step, we employ stochastic gradient Hamiltonian Monte Carlo with budget-awareness to generate sub-networks, which allows large search space with efficient computation. In the estimation step, we deduce the sub-network sampler to a near-optimal point, to promote the generation of high-quality sub-networks. Unifying the exploration and estimation, our approach avoids early falling into local minimum via a fast gradient-based search in a larger space. Extensive experiments on CIFAR-10 and ImageNet show that our method achieves state-of-the-art performances on pruning several popular CNNs.

Fredrik K. Gustafsson, Martin Danelljan, Goutam Bhat, Thomas B. Schön

While deep learning-based classification is generally tackled using standardized approaches, a wide variety of techniques are employed for regression. In computer vision, one particularly popular such technique is that of confidence-based regression, which entails predicting a confidence value for each input-target pair $(x, y)$. While this approach has demonstrated impressive results, it requires important task-dependent design choices, and the predicted confidences lack a natural probabilistic meaning. We address these issues by proposing a general and conceptually simple regression method with a clear probabilistic interpretation. In our proposed approach, we create an energy-based model of the conditional target density $p(y | x)$, using a deep neural network to predict the un-normalized density from $(x, y)$. This model of $p(y | x)$ is trained by directly minimizing the associated negative log-likelihood, approximated using Monte Carlo sampling. We perform comprehensive experiments on four computer vision regression tasks. Our approach outperforms direct regression, as well as other probabilistic and confidence-based methods. Notably, our model achieves a $2.2\%$ AP improvement over Faster-RCNN for object detection on the COCO dataset, and sets a new state-of-the-art on visual tracking when applied for bounding box estimation. In contrast to confidence-based methods, our approach is also shown to be directly applicable to more general tasks such as age and head-pose estimation. Code is available at https://github.com/fregu856/ebms_regression.

Yifan Xu, Tianqi Fan, Yi Yuan, Gurprit Singh

Deep implicit field regression methods are effective for 3D reconstruction from single-view images. However, the impact of different sampling patterns on the reconstruction quality is not well-understood. In this work, we first study the effect of point set discrepancy on the network training. Based on Farthest Point Sampling algorithm, we propose a sampling scheme that theoretically encourages better generalization performance, and results in fast convergence for SGD-based optimization algorithms. Secondly, based on the reflective symmetry of an object, we propose a feature fusion method that alleviates issues due to self-occlusions which makes it difficult to utilize local image features. Our proposed system Ladybird is able to create high quality 3D object reconstructions from a single input image. We evaluate Ladybird on a large scale 3D dataset (ShapeNet) demonstrating highly competitive results in terms of Chamfer distance, Earth Mover's distance and Intersection Over Union (IoU).