The robust constrained Markov decision process (RCMDP) is a recent task-modelling framework for reinforcement learning that incorporates behavioural constraints and that provides robustness to errors in the transition dynamics model through the use of an uncertainty set. Simulating RCMDPs requires computing the worst-case dynamics based on value estimates for each state, an approach which has previously been used in the Robust Constrained Policy Gradient (RCPG). Highlighting potential downsides of RCPG such as not robustifying the full constrained objective and the lack of incremental learning, this paper introduces two algorithms, called RCPG with Robust Lagrangian and Adversarial RCPG. RCPG with Robust Lagrangian modifies RCPG by taking the worst-case dynamics based on the Lagrangian rather than either the value or the constraint. Adversarial RCPG also formulates the worst-case dynamics based on the Lagrangian but learns this directly and incrementally as an adversarial policy through gradient descent rather than indirectly and abruptly through constrained optimisation on a sorted value list. A theoretical analysis first derives the Lagrangian policy gradient for the policy optimisation of both proposed algorithms and then the adversarial policy gradient to learn the adversary for Adversarial RCPG. Empirical experiments injecting perturbations in inventory management and safe navigation tasks demonstrate the competitive performance of both algorithms compared to traditional RCPG variants as well as non-robust and non-constrained ablations. In particular, Adversarial RCPG ranks among the top two performing algorithms on all tests.
相關內容
In offline reinforcement learning (RL), the absence of active exploration calls for attention on the model robustness to tackle the sim-to-real gap, where the discrepancy between the simulated and deployed environments can significantly undermine the performance of the learned policy. To endow the learned policy with robustness in a sample-efficient manner in the presence of high-dimensional state-action space, this paper considers the sample complexity of distributionally robust linear Markov decision processes (MDPs) with an uncertainty set characterized by the total variation distance using offline data. We develop a pessimistic model-based algorithm and establish its sample complexity bound under minimal data coverage assumptions, which outperforms prior art by at least $\widetilde{O}(d)$, where $d$ is the feature dimension. We further improve the performance guarantee of the proposed algorithm by incorporating a carefully-designed variance estimator.
Performance modeling is an essential tool in many areas, including performance characterization/optimization, design space exploration, and resource allocation problems, to name a few. However, existing performance modeling approaches have limitations, such as high computational cost for discrete-event simulators, narrow flexibility of hardware emulators, or restricted accuracy/generality of analytical/data-driven models. To address these limitations, this paper proposes PerfVec, a novel deep learning-based performance modeling framework that learns high-dimensional and independent/orthogonal program and microarchitecture representations. Once learned, a program representation can be used to predict its performance on any microarchitecture, and likewise, a microarchitecture representation can be applied in the performance prediction of any program. Additionally, PerfVec yields a foundation model that captures the performance essence of instructions, which can be directly used by developers in numerous performance modeling related tasks without incurring its training cost. The evaluation demonstrates that PerfVec is more general and efficient than previous approaches.
Leveraging the computing and sensing capabilities of vehicles, vehicular federated learning (VFL) has been applied to edge training for connected vehicles. The dynamic and interconnected nature of vehicular networks presents unique opportunities to harness direct vehicle-to-vehicle (V2V) communications, enhancing VFL training efficiency. In this paper, we formulate a stochastic optimization problem to optimize the VFL training performance, considering the energy constraints and mobility of vehicles, and propose a V2V-enhanced dynamic scheduling (VEDS) algorithm to solve it. The model aggregation requirements of VFL and the limited transmission time due to mobility result in a stepwise objective function, which presents challenges in solving the problem. We thus propose a derivative-based drift-plus-penalty method to convert the long-term stochastic optimization problem to an online mixed integer nonlinear programming (MINLP) problem, and provide a theoretical analysis to bound the performance gap between the online solution and the offline optimal solution. Further analysis of the scheduling priority reduces the original problem into a set of convex optimization problems, which are efficiently solved using the interior-point method. Experimental results demonstrate that compared with the state-of-the-art benchmarks, the proposed algorithm enhances the image classification accuracy on the CIFAR-10 dataset by 3.18% and reduces the average displacement errors on the Argoverse trajectory prediction dataset by 10.21%.
Quantum machine learning (QML) is a rapidly expanding field that merges the principles of quantum computing with the techniques of machine learning. One of the powerful mathematical frameworks in this domain is tensor networks. These networks are used to approximate high-order tensors by contracting tensors with lower ranks. Originally developed for simulating quantum systems, tensor networks have become integral to quantum computing and, by extension, to QML. Their ability to efficiently represent and manipulate complex, high-dimensional data makes them suitable for various machine learning tasks within the quantum realm. Here, we present a matrix product state (MPS) model, where the MPS functions as both a classifier and a generator. The dual functionality of this novel MPS model permits a strategy that enhances the traditional training of supervised MPS models. This framework is inspired by generative adversarial networks and is geared towards generating more realistic samples by reducing outliers. Additionally, our contributions offer insights into the mechanics of tensor network methods for generation tasks. Specifically, we discuss alternative embedding functions and a new sampling method from non-normalized MPSs.
In the context of machine unlearning, the primary challenge lies in effectively removing traces of private data from trained models while maintaining model performance and security against privacy attacks like membership inference attacks. Traditional gradient-based unlearning methods often rely on extensive historical gradients, which becomes impractical with high unlearning ratios and may reduce the effectiveness of unlearning. Addressing these limitations, we introduce Mini-Unlearning, a novel approach that capitalizes on a critical observation: unlearned parameters correlate with retrained parameters through contraction mapping. Our method, Mini-Unlearning, utilizes a minimal subset of historical gradients and leverages this contraction mapping to facilitate scalable, efficient unlearning. This lightweight, scalable method significantly enhances model accuracy and strengthens resistance to membership inference attacks. Our experiments demonstrate that Mini-Unlearning not only works under higher unlearning ratios but also outperforms existing techniques in both accuracy and security, offering a promising solution for applications requiring robust unlearning capabilities.
Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing the generalization capabilities of a model, it can also address many other challenges and problems, from overcoming a limited amount of training data over regularizing the objective to limiting the amount data used to protect privacy. Based on a precise description of the goals and applications of data augmentation (C1) and a taxonomy for existing works (C2), this survey is concerned with data augmentation methods for textual classification and aims to achieve a concise and comprehensive overview for researchers and practitioners (C3). Derived from the taxonomy, we divided more than 100 methods into 12 different groupings and provide state-of-the-art references expounding which methods are highly promising (C4). Finally, research perspectives that may constitute a building block for future work are given (C5).
There has been appreciable progress in unsupervised network representation learning (UNRL) approaches over graphs recently with flexible random-walk approaches, new optimization objectives and deep architectures. However, there is no common ground for systematic comparison of embeddings to understand their behavior for different graphs and tasks. In this paper we theoretically group different approaches under a unifying framework and empirically investigate the effectiveness of different network representation methods. In particular, we argue that most of the UNRL approaches either explicitly or implicit model and exploit context information of a node. Consequently, we propose a framework that casts a variety of approaches -- random walk based, matrix factorization and deep learning based -- into a unified context-based optimization function. We systematically group the methods based on their similarities and differences. We study the differences among these methods in detail which we later use to explain their performance differences (on downstream tasks). We conduct a large-scale empirical study considering 9 popular and recent UNRL techniques and 11 real-world datasets with varying structural properties and two common tasks -- node classification and link prediction. We find that there is no single method that is a clear winner and that the choice of a suitable method is dictated by certain properties of the embedding methods, task and structural properties of the underlying graph. In addition we also report the common pitfalls in evaluation of UNRL methods and come up with suggestions for experimental design and interpretation of results.
Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for NMT.
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the difference between the actions committed by the expert (or ground truth) and the agent among complicated states in the environment. EE task benefits from these dynamic rewards because instances and labels yield to various extents of difficulty and the gains are expected to be diverse -- e.g., an ambiguous but correctly detected trigger or argument should receive high gains -- while the traditional RL models usually neglect such differences and pay equal attention on all instances. Moreover, our experiments also demonstrate that the proposed framework outperforms state-of-the-art methods, without explicit feature engineering.
Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the original combinatorial problem, and turns a broad class of DP algorithms into differentiable operators. Theoretically, we provide a new probabilistic perspective on backpropagating through these DP operators, and relate them to inference in graphical models. We derive two particular instantiations of our framework, a smoothed Viterbi algorithm for sequence prediction and a smoothed DTW algorithm for time-series alignment. We showcase these instantiations on two structured prediction tasks and on structured and sparse attention for neural machine translation.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191