In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the multi-objective setting in order to achieve the above goal. However, such methods face a new challenge in offline MORL settings, namely the preference-inconsistent demonstration problem. We propose two solutions to this problem: 1) filtering out preference-inconsistent demonstrations via approximating behavior preferences, and 2) adopting regularization techniques with high policy expressiveness. Moreover, we integrate the preference-conditioned scalarized update method into policy-regularized offline RL, in order to simultaneously learn a set of policies using a single policy network, thus reducing the computational cost induced by the training of a large number of individual policies for various preferences. Finally, we introduce Regularization Weight Adaptation to dynamically determine appropriate regularization weights for arbitrary target preferences during deployment. Empirical results on various multi-objective datasets demonstrate the capability of our approach in solving offline MORL problems.
相關內容
In this paper, we apply quasi-Monte Carlo (QMC) methods with an initial preintegration step to estimate cumulative distribution functions and probability density functions in uncertainty quantification (UQ). The distribution and density functions correspond to a quantity of interest involving the solution to an elliptic partial differential equation (PDE) with a lognormally distributed coefficient and a normally distributed source term. There is extensive previous work on using QMC to compute expected values in UQ, which have proven very successful in tackling a range of different PDE problems. However, the use of QMC for density estimation applied to UQ problems will be explored here for the first time. Density estimation presents a more difficult challenge compared to computing the expected value due to discontinuities present in the integral formulations of both the distribution and density. Our strategy is to use preintegration to eliminate the discontinuity by integrating out a carefully selected random parameter, so that QMC can be used to approximate the remaining integral. First, we establish regularity results for the PDE quantity of interest that are required for smoothing by preintegration to be effective. We then show that an $N$-point lattice rule can be constructed for the integrands corresponding to the distribution and density, such that after preintegration the QMC error is of order $\mathcal{O}(N^{-1+\epsilon})$ for arbitrarily small $\epsilon>0$. This is the same rate achieved for computing the expected value of the quantity of interest. Numerical results are presented to reaffirm our theory.
As Internet censors rapidly evolve new blocking techniques, circumvention tools must also adapt and roll out new strategies to remain unblocked. But new strategies can be time consuming for circumventors to develop and deploy, and usually an update to one tool often requires significant additional effort to be ported to others. Moreover, distributing the updated application across different platforms poses its own set of challenges. In this paper, we introduce WATER (WebAssembly Transport Executables Runtime), a novel design that enables applications to use a WebAssembly-based application-layer (e.g., TLS) to wrap network connections and provide network transports. Deploying a new circumvention technique with WATER only requires distributing the WebAssembly Transport Module(WATM) binary and any transport-specific configuration, allowing dynamic transport updates without any change to the application itself. WATMs are also designed to be generic such that different applications using WATER can use the same WATM to rapidly deploy successful circumvention techniques to their own users, facilitating rapid interoperability between independent circumvention tools.
In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples. This understanding leads us to the development of Batch-ICL, an effective, efficient, and order-agnostic inference algorithm for ICL. Differing from the standard N-shot learning approach, Batch-ICL employs $N$ separate 1-shot forward computations and aggregates the resulting meta-gradients. These aggregated meta-gradients are then applied to the forward computation of a zero-shot query to generate the final prediction. This batch processing approach renders the LLM agnostic to the order of ICL examples. Through extensive experiments and analysis, we demonstrate that Batch-ICL consistently outperforms most permutations of ICL examples. In some cases, it even exceeds the performance of the best order for standard ICL, all while reducing the computational resources required. Furthermore, we develop a novel variant of Batch-ICL featuring multiple "epochs" of meta-optimization. This variant implicitly explores permutations of ICL examples, further enhancing ICL performance.
Inferring the types of API elements in incomplete code snippets (e.g., those on Q&A forums) is a prepositive step required to work with the code snippets. Existing type inference methods can be mainly categorized as constraint-based or statistically-based. The former imposes higher requirements on code syntax and often suffers from low recall due to the syntactic limitation of code snippets. The latter relies on the statistical regularities learned from a training corpus and does not take full advantage of the type constraints in code snippets, which may lead to low precision. In this paper, we propose an iterative type inference framework for Java, called iJTyper, by integrating the strengths of both constraint- and statistically-based methods. For a code snippet, iJTyper first applies a constraint-based method and augments the code context with the inferred types of API elements. iJTyper then applies a statistically-based method to the augmented code snippet. The predicted candidate types of API elements are further used to improve the constraint-based method by reducing its pre-built knowledge base. iJTyper iteratively executes both methods and performs code context augmentation and knowledge base reduction until a termination condition is satisfied. Finally, the final inference results are obtained by combining the results of both methods. We evaluated iJTyper on two open-source datasets. Results show that 1) iJTyper achieves high average precision/recall of 97.31% and 92.52% on both datasets; 2) iJTyper significantly improves the recall of two state-of-the-art baselines, SnR and MLMTyper, by at least 7.31% and 27.44%, respectively; and 3) iJTyper improves the average precision/recall of the popular language model, ChatGPT, by 3.25% and 0.51% on both datasets.
Being one of the IR-NAT (Iterative-refinemennt-based NAT) frameworks, the Conditional Masked Language Model (CMLM) adopts the mask-predict paradigm to re-predict the masked low-confidence tokens. However, CMLM suffers from the data distribution discrepancy between training and inference, where the observed tokens are generated differently in the two cases. In this paper, we address this problem with the training approaches of error exposure and consistency regularization (EECR). We construct the mixed sequences based on model prediction during training, and propose to optimize over the masked tokens under imperfect observation conditions. We also design a consistency learning method to constrain the data distribution for the masked tokens under different observing situations to narrow down the gap between training and inference. The experiments on five translation benchmarks obtains an average improvement of 0.68 and 0.40 BLEU scores compared to the base models, respectively, and our CMLMC-EECR achieves the best performance with a comparable translation quality with the Transformer. The experiments results demonstrate the effectiveness of our method.
We consider an interesting problem-salient instance segmentation in this paper. Other than producing bounding boxes, our network also outputs high-quality instance-level segments. Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch. Our new branch regards not only local context inside each detection window but also its surrounding context, enabling us to distinguish the instances in the same scope even with obstruction. Our network is end-to-end trainable and runs at a fast speed (40 fps when processing an image with resolution 320x320). We evaluate our approach on a publicly available benchmark and show that it outperforms other alternative solutions. We also provide a thorough analysis of the design choices to help readers better understand the functions of each part of our network. The source code can be found at \url{//github.com/RuochenFan/S4Net}.
BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks. In this paper, we describe BERTSUM, a simple variant of BERT, for extractive summarization. Our system is the state of the art on the CNN/Dailymail dataset, outperforming the previous best-performed system by 1.65 on ROUGE-L. The codes to reproduce our results are available at //github.com/nlpyang/BertSum
In this paper, we focus on three problems in deep learning based medical image segmentation. Firstly, U-net, as a popular model for medical image segmentation, is difficult to train when convolutional layers increase even though a deeper network usually has a better generalization ability because of more learnable parameters. Secondly, the exponential ReLU (ELU), as an alternative of ReLU, is not much different from ReLU when the network of interest gets deep. Thirdly, the Dice loss, as one of the pervasive loss functions for medical image segmentation, is not effective when the prediction is close to ground truth and will cause oscillation during training. To address the aforementioned three problems, we propose and validate a deeper network that can fit medical image datasets that are usually small in the sample size. Meanwhile, we propose a new loss function to accelerate the learning process and a combination of different activation functions to improve the network performance. Our experimental results suggest that our network is comparable or superior to state-of-the-art methods.
Recommender systems are widely used in big information-based companies such as Google, Twitter, LinkedIn, and Netflix. A recommender system deals with the problem of information overload by filtering important information fragments according to users' preferences. In light of the increasing success of deep learning, recent studies have proved the benefits of using deep learning in various recommendation tasks. However, most proposed techniques only aim to target individuals, which cannot be efficiently applied in group recommendation. In this paper, we propose a deep learning architecture to solve the group recommendation problem. On the one hand, as different individual preferences in a group necessitate preference trade-offs in making group recommendations, it is essential that the recommendation model can discover substitutes among user behaviors. On the other hand, it has been observed that a user as an individual and as a group member behaves differently. To tackle such problems, we propose using an attention mechanism to capture the impact of each user in a group. Specifically, our model automatically learns the influence weight of each user in a group and recommends items to the group based on its members' weighted preferences. We conduct extensive experiments on four datasets. Our model significantly outperforms baseline methods and shows promising results in applying deep learning to the group recommendation problem.
This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence. We also propose a self-attention mechanism and a special regularization term for the model. As a side effect, the embedding comes with an easy way of visualizing what specific parts of the sentence are encoded into the embedding. We evaluate our model on 3 different tasks: author profiling, sentiment classification, and textual entailment. Results show that our model yields a significant performance gain compared to other sentence embedding methods in all of the 3 tasks.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191