亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

While large language models (LLMs) have enabled learning knowledge from the pre-training corpora, the acquired knowledge may be fundamentally incorrect or outdated over time, which necessitates rectifying the knowledge of the language model (LM) after the training. A promising approach involves employing a hyper-network to generate parameter shift, whereas existing hyper-networks suffer from inferior scalability in synchronous editing operation amount. To mitigate the problem, we propose the MAssive Language Model Editing Network (MALMEN), which formulates the parameter shift aggregation as the least square problem, subsequently updating the LM parameters using the normal equation. To accommodate editing multiple facts simultaneously with limited memory budgets, we separate the computation on the hyper-network and LM, enabling arbitrary batch size on both neural networks. Our method is evaluated by editing up to thousands of facts on LMs with different architectures, i.e., BERT-base, GPT-2, T5-XL (2.8B), and GPT-J (6B), across various knowledge-intensive NLP tasks, i.e., closed book fact-checking and question answering. Remarkably, MALMEN is capable of editing hundreds of times more facts than strong baselines with the identical hyper-network architecture and outperforms editor specifically designed for GPT. Our code is available at //github.com/ChenmienTan/malmen.

Reinforcement learning has been successful across several applications in which agents have to learn to act in environments with sparse feedback. However, despite this empirical success there is still a lack of theoretical understanding of how the parameters of reinforcement learning models and the features used to represent states interact to control the dynamics of learning. In this work, we use concepts from statistical physics, to study the typical case learning curves for temporal difference learning of a value function with linear function approximators. Our theory is derived under a Gaussian equivalence hypothesis where averages over the random trajectories are replaced with temporally correlated Gaussian feature averages and we validate our assumptions on small scale Markov Decision Processes. We find that the stochastic semi-gradient noise due to subsampling the space of possible episodes leads to significant plateaus in the value error, unlike in traditional gradient descent dynamics. We study how learning dynamics and plateaus depend on feature structure, learning rate, discount factor, and reward function. We then analyze how strategies like learning rate annealing and reward shaping can favorably alter learning dynamics and plateaus. To conclude, our work introduces new tools to open a new direction towards developing a theory of learning dynamics in reinforcement learning.

Recently, SimCSE has shown the feasibility of contrastive learning in training sentence embeddings and illustrates its expressiveness in spanning an aligned and uniform embedding space. However, prior studies have shown that dense models could contain harmful parameters that affect the model performance, and it is no wonder that SimCSE can as well be invented with such parameters. Driven by this, parameter sparsification is applied, where alignment and uniformity scores are used to measure the contribution of each parameter to the overall quality of sentence embeddings. Drawing from a preliminary study, we consider parameters with minimal contributions to be detrimental, as their sparsification results in improved model performance. To discuss the ubiquity of detrimental parameters and remove them, more experiments on the standard semantic textual similarity (STS) tasks and transfer learning tasks are conducted, and the results show that the proposed sparsified SimCSE (SparseCSE) has excellent performance in comparison with SimCSE. Furthermore, through in-depth analysis, we establish the validity and stability of our sparsification method, showcasing that the embedding space generated by SparseCSE exhibits improved alignment compared to that produced by SimCSE. Importantly, the uniformity yet remains uncompromised.

Commutativity has proven to be a powerful tool in reasoning about concurrent programs. Recent work has shown that a commutativity-based reduction of a program may admit simpler proofs than the program itself. The framework of lexicographical program reductions was introduced to formalize a broad class of reductions. Approaches based on this framework, however, were limited to program models with a fixed number of threads. In this paper, we show that it is possible to define an effective parametric family of program reductions that can be used to find simple proofs for parameterized programs, i.e., programs with an unbounded number of threads. We show that reductions are indeed useful for the simplification of proofs of parameterized programs, in a sense that can be made precise: A reduction of a parameterized program may admit a proof which uses fewer or less sophisticated ghost variables. The reduction may therefore be within reach of an automated verification technique, even when the original parameterized program is not. We introduce a notion of reductions for parameterized programs such that the reduction $\mathcal{R}$ of a parameterized program $\mathcal{P}$ is again a parameterized program (the thread template of $\mathcal{R}$ is obtained by source-to-source transformation of the thread template of $\mathcal{P}$). Consequently, existing techniques for the verification of parameterized programs can be directly applied to $\mathcal{R}$ instead of $\mathcal{P}$. We define an appropriate family of pairwise preference orders which can be used to produce different lexicographical reductions. To determine whether this theoretical foundation amounts to a usable solution in practice, we have implemented the approach, based on a recently proposed framework for parameterized program verification. The results of our preliminary experiments on a representative set of examples are encouraging.

In Programming by Demonstration, the robot learns novel skills from human demonstrations. After learning, the robot should be able not only to reproduce the skill, but also to generalize it to shifted domains without collecting new training data. Adaptation to similar domains has been investigated in the literature; however, an open problem is how to adapt learned skills to different conditions that are outside of the data distribution, and, more important, how to preserve the precision of the desired adaptations. This paper presents a novel supervised learning framework called Constrained Equation Learner Networks that addresses the trajectory adaptation problem in Programming by Demonstrations from a constrained regression perspective. While conventional approaches for constrained regression use one kind of basis function, e.g., Gaussian, we exploit Equation Learner Networks to learn a set of analytical expressions and use them as basis functions. These basis functions are learned from demonstration with the objective to minimize deviations from the training data while imposing constraints that represent the desired adaptations, like new initial or final points or maintaining the trajectory within given bounds. Our approach addresses three main difficulties in adapting robotic trajectories: 1) minimizing the distortion of the trajectory for new adaptations; 2) preserving the precision of the adaptations; and 3) dealing with the lack of intuition about the structure of basis functions. We validate our approach both in simulation and in real experiments in a set of robotic tasks that require adaptation due to changes in the environment, and we compare obtained results with two existing approaches. Performed experiments show that Constrained Equation Learner Networks outperform state of the art approaches by increasing generalization and adaptability of robotic skills.

While there now exists a large literature on policy evaluation and learning, much of prior work assumes that the treatment assignment of one unit does not affect the outcome of another unit. Unfortunately, ignoring interference may lead to biased policy evaluation and yield ineffective learned policies. For example, treating influential individuals who have many friends can generate positive spillover effects, thereby improving the overall performance of an individualized treatment rule (ITR). We consider the problem of evaluating and learning an optimal ITR under clustered network (or partial) interference where clusters of units are sampled from a population and units may influence one another within each cluster. Under this model, we propose an estimator that can be used to evaluate the empirical performance of an ITR. We show that this estimator is substantially more efficient than the standard inverse probability weighting estimator, which does not impose any assumption about spillover effects. We derive the finite-sample regret bound for a learned ITR, showing that the use of our efficient evaluation estimator leads to the improved performance of learned policies. Finally, we conduct simulation and empirical studies to illustrate the advantages of the proposed methodology.

Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation, a data mining approach for imbalanced learning, has been used to improve this generalization. However, it is unclear whether SMOTE also benefits deep learning. In this work, we study why the original SMOTE is insufficient for deep learning, and enhance SMOTE using soft labels. Connecting the resulting soft SMOTE with Mixup, a modern data augmentation technique, leads to a unified framework that puts traditional and modern data augmentation techniques under the same umbrella. A careful study within this framework shows that Mixup improves generalization by implicitly achieving uneven margins between majority and minority classes. We then propose a novel margin-aware Mixup technique that more explicitly achieves uneven margins. Extensive experimental results demonstrate that our proposed technique yields state-of-the-art performance on deep imbalanced classification while achieving superior performance on extremely imbalanced data. The code is open-sourced in our developed package //github.com/ntucllab/imbalanced-DL to foster future research in this direction.

Attention Model has now become an important concept in neural networks that has been researched within diverse application domains. This survey provides a structured and comprehensive overview of the developments in modeling attention. In particular, we propose a taxonomy which groups existing techniques into coherent categories. We review salient neural architectures in which attention has been incorporated, and discuss applications in which modeling attention has shown a significant impact. Finally, we also describe how attention has been used to improve the interpretability of neural networks. We hope this survey will provide a succinct introduction to attention models and guide practitioners while developing approaches for their applications.

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.

Text Classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.