Action anticipation involves predicting future actions having observed the initial portion of a video. Typically, the observed video is processed as a whole to obtain a video-level representation of the ongoing activity in the video, which is then used for future prediction. We introduce Anticipatr which performs long-term action anticipation leveraging segment-level representations learned using individual segments from different activities, in addition to a video-level representation. We propose a two-stage learning approach to train a novel transformer-based model that uses these two types of representations to directly predict a set of future action instances over any given anticipation duration. Results on Breakfast, 50Salads, Epic-Kitchens-55, and EGTEA Gaze+ datasets demonstrate the effectiveness of our approach.

The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing. In this work, we introduce a parameter-compositional approach (PaCo) as an attempt to address these challenges. In this framework, a policy subspace represented by a set of parameters is learned. Policies for all the single tasks lie in this subspace and can be composed by interpolating with the learned set. It allows not only flexible parameter sharing but also a natural way to improve training. We demonstrate the state-of-the-art performance on Meta-World benchmarks, verifying the effectiveness of the proposed approach.

In the machine learning literature stochastic gradient descent has recently been widely discussed for its purported implicit regularization properties. Much of the theory, that attempts to clarify the role of noise in stochastic gradient algorithms, has widely approximated stochastic gradient descent by a stochastic differential equation with Gaussian noise. We provide a novel rigorous theoretical justification for this practice that showcases how the Gaussianity of the noise arises naturally.

We study momentum-based first-order optimization algorithms in which the iterations utilize information from the two previous steps and are subject to an additive white noise. This class of algorithms includes Polyak's heavy-ball and Nesterov's accelerated methods as special cases and noise accounts for uncertainty in either gradient evaluation or iteration updates. For strongly convex quadratic problems, we use the steady-state variance of the error in the optimization variable to quantify noise amplification and identify fundamental stochastic performance tradeoffs. Our approach utilizes the Jury stability criterion to provide a novel geometric characterization of conditions for linear convergence, and it clarifies the relation between the noise amplification and convergence rate as well as their dependence on the condition number and the constant algorithmic parameters. This geometric insight leads to simple alternative proofs of standard convergence results and allows us to establish analytical lower bounds on the product between the settling time and noise amplification that scale quadratically with the condition number. Our analysis also identifies a key difference between the gradient and iterate noise models: while the amplification of gradient noise can be made arbitrarily small by sufficiently decelerating the algorithm, the best achievable variance amplification for the iterate noise model increases linearly with the settling time in decelerating regime. Furthermore, we introduce two parameterized families of algorithms that strike a balance between noise amplification and settling time while preserving order-wise Pareto optimality for both noise models. Finally, by analyzing a class of accelerated gradient flow dynamics, whose suitable discretization yields the two-step momentum algorithm, we establish that stochastic performance tradeoffs also extend to continuous time.

In the past few years, graph neural networks (GNNs) have become the de facto model of choice for graph classification. While, from the theoretical viewpoint, most GNNs can operate on graphs of any size, it is empirically observed that their classification performance degrades when they are applied on graphs with sizes that differ from those in the training data. Previous works have tried to tackle this issue in graph classification by providing the model with inductive biases derived from assumptions on the generative process of the graphs, or by requiring access to graphs from the test domain. The first strategy is tied to the quality of the assumptions made for the generative process, and requires the use of specific models designed after the explicit definition of the generative process of the data, leaving open the question of how to improve the performance of generic GNN models in general settings. On the other hand, the second strategy can be applied to any GNN, but requires access to information that is not always easy to obtain. In this work we consider the scenario in which we only have access to the training data, and we propose a regularization strategy that can be applied to any GNN to improve its generalization capabilities from smaller to larger graphs without requiring access to the test data. Our regularization is based on the idea of simulating a shift in the size of the training graphs using coarsening techniques, and enforcing the model to be robust to such a shift. Experimental results on standard datasets show that popular GNN models, trained on the 50% smallest graphs in the dataset and tested on the 10% largest graphs, obtain performance improvements of up to 30% when trained with our regularization strategy.

Transformer-based QG models can generate question-answer pairs (QAPs) with high qualities, but may also generate silly questions for certain texts. We present a new method called tag-set sequence learning to tackle this problem, where a tag-set sequence is a sequence of tag sets to capture the syntactic and semantic information of the underlying sentence, and a tag set consists of one or more language feature tags, including, for example, semantic-role-labeling, part-of-speech, named-entity-recognition, and sentiment-indication tags. We construct a system called TSS-Learner to learn tag-set sequences from given declarative sentences and the corresponding interrogative sentences, and derive answers to the latter. We train a TSS-Learner model for the English language using a small training dataset and show that it can indeed generate adequate QAPs for certain texts that transformer-based models do poorly. Human evaluation on the QAPs generated by TSS-Learner over SAT practice reading tests is encouraging.

Imitation learning aims to extract knowledge from human experts' demonstrations or artificially created agents in order to replicate their behaviors. Its success has been demonstrated in areas such as video games, autonomous driving, robotic simulations and object manipulation. However, this replicating process could be problematic, such as the performance is highly dependent on the demonstration quality, and most trained agents are limited to perform well in task-specific environments. In this survey, we provide a systematic review on imitation learning. We first introduce the background knowledge from development history and preliminaries, followed by presenting different taxonomies within Imitation Learning and key milestones of the field. We then detail challenges in learning strategies and present research opportunities with learning policy from suboptimal demonstration, voice instructions and other associated optimization schemes.

We study geodesically convex (g-convex) problems that can be written as a difference of Euclidean convex functions. This structure arises in several optimization problems in statistics and machine learning, e.g., for matrix scaling, M-estimators for covariances, and Brascamp-Lieb inequalities. Our work offers efficient algorithms that on the one hand exploit g-convexity to ensure global optimality along with guarantees on iteration complexity. On the other hand, the split structure permits us to develop Euclidean Majorization-Minorization algorithms that help us bypass the need to compute expensive Riemannian operations such as exponential maps and parallel transport. We illustrate our results by specializing them to a few concrete optimization problems that have been previously studied in the machine learning literature. Ultimately, we hope our work helps motivate the broader search for mixed Euclidean-Riemannian optimization algorithms

The current paper concerns language transfer at the phonetic level and concentrates on the transfer phenomenon in an advanced English language learner's acquisition of the English vowels /i/ and its lax counterpart. By determining whether the Chinese English-language learner (ELL), named Vanya, can accurately distinguish between /i/ and its lax counterpart, and pronounce them precisely in General American English (GAE), this paper serves as a reference for further studying language transfer among Chinese ELLs. There were two objectives: first, the learner's perceptual ability to distinguish between vowels /i/ and its lax counterpart was examined; second, the effect of the phonetic transfer was determined. Two perception tests and a production test were used to attain these two objectives. The results of two perception tests demonstrated Vanya's perceptual competence in distinguishing between /i/ and its lax counterpart and laid a solid foundation for the validity of the subsequent production test. Given that Vanya's production of F1 and F2 values of /i/ were highly similar across his first language (Mandarin Chinese) and second language (GAE) and that both values were lower than the typical values for common /i/ in GAE, with an especially prominent disparity between the F2 values, it is reasonable to conclude that a phonetic transfer occurred. The participant's high perceptual competence as an advanced-level ELL did not noticeably moderate the effect of phonetic transfer.

A key part of learning to program is learning to understand programming error messages. They can be hard to interpret and identifying the cause of errors can be time-consuming. One factor in this challenge is that the messages are typically intended for an audience that already knows how to program, or even for programming environments that then use the information to highlight areas in code. Researchers have been working on making these errors more novice friendly since the 1960s, however progress has been slow. The present work contributes to this stream of research by using large language models to enhance programming error messages with explanations of the errors and suggestions on how to fix the error. Large language models can be used to create useful and novice-friendly enhancements to programming error messages that sometimes surpass the original programming error messages in interpretability and actionability. These results provide further evidence of the benefits of large language models for computing educators, highlighting their use in areas known to be challenging for students. We further discuss the benefits and downsides of large language models and highlight future streams of research for enhancing programming error messages.