We present a new distribution-free conformal prediction algorithm for sequential data (e.g., time series), called the \textit{sequential predictive conformal inference} (\texttt{SPCI}). We specifically account for the nature that time series data are non-exchangeable, and thus many existing conformal prediction algorithms are not applicable. The main idea is to adaptively re-estimate the conditional quantile of non-conformity scores (e.g., prediction residuals), upon exploiting the temporal dependence among them. More precisely, we cast the problem of conformal prediction interval as predicting the quantile of a future residual, given a user-specified point prediction algorithm. Theoretically, we establish asymptotic valid conditional coverage upon extending consistency analyses in quantile regression. Using simulation and real-data experiments, we demonstrate a significant reduction in interval width of \texttt{SPCI} compared to other existing methods under the desired empirical coverage.

PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation bounds as training objectives. Most of the exisiting bounds involve a \emph{Kullback-Leibler} (KL) divergence, which fails to capture the geometric properties of the loss function which are often useful in optimisation. We address this by extending the emerging \emph{Wasserstein PAC-Bayes} theory. We develop new PAC-Bayes bounds with Wasserstein distances replacing the usual KL, and demonstrate that sound optimisation guarantees translate to good generalisation abilities. In particular we provide generalisation bounds for the \emph{Bures-Wasserstein SGD} by exploiting its optimisation properties.

We design and evaluate a Bayesian optimization framework for resource efficient pre-training of Transformer-based language models (TLMs). TLM pre-training requires high computational resources and introduces many unresolved design choices, such as selecting its pre-training hyperparameters. We propose a multi-armed bandit framework for the sequential selection of TLM pre-training hyperparameters, aimed at optimizing language model performance, in a resource efficient manner. We design a Thompson sampling algorithm, with a surrogate Gaussian process reward model of the Masked Language Model (MLM) pre-training objective, for its sequential minimization. Instead of MLM pre-training with fixed masking probabilities, the proposed Gaussian process-based Thompson sampling (GP-TS) accelerates pre-training by sequentially selecting masking hyperparameters that improve performance. We empirically demonstrate how GP-TS pre-trains language models efficiently, i.e., it achieves lower MLM loss in fewer epochs, across a variety of settings. In addition, GP-TS pre-trained TLMs attain competitive downstream performance, while avoiding expensive hyperparameter grid search. GP-TS provides an interactive framework for efficient and optimized TLM pre-training that, by circumventing costly hyperparameter selection, enables substantial computational savings.

This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a neural network, which can be optimised using cross-entropy loss or Arcface loss, to measure the similarity of a synthetic data to real speech. We found that incorporating synthetic samples with considerable dissimilarity to real speech, owing in part to lexical differences, into ASR training is crucial for boosting recognition performance. Experimental results on Librispeech test sets indicate that, in order to maintain the same speech recognition accuracy as when using all TTS data, our proposed solution can reduce the size of the TTS data down below its $30\,\%$, which is superior to several baseline methods.

This paper presents an efficient hardware implementation of the recently proposed Optimized Deep Event-driven Spiking Neural Network Architecture (ODESA). ODESA is the first network to have end-to-end multi-layer online local supervised training without using gradients and has the combined adaptation of weights and thresholds in an efficient hierarchical structure. This research shows that the network architecture and the online training of weights and thresholds can be implemented efficiently on a large scale in hardware. The implementation consists of a multi-layer Spiking Neural Network (SNN) and individual training modules for each layer that enable online self-learning without using back-propagation. By using simple local adaptive selection thresholds, a Winner-Takes-All (WTA) constraint on each layer, and a modified weight update rule that is more amenable to hardware, the trainer module allocates neuronal resources optimally at each layer without having to pass high-precision error measurements across layers. All elements in the system, including the training module, interact using event-based binary spikes. The hardware-optimized implementation is shown to preserve the performance of the original algorithm across multiple spatial-temporal classification problems with significantly reduced hardware requirements.

Dealing with representation shift is one of the main problems in online continual learning. Current methods mainly solve this by reducing representation shift, but leave the classifier on top of the representation to slowly adapt, in many update steps, to the remaining representation shift, increasing forgetting. We propose DeepCCG, an empirical Bayesian approach to solve this problem. DeepCCG works by updating the posterior of a class conditional Gaussian classifier such that the classifier adapts instantly to representation shift. The use of a class conditional Gaussian classifier also enables DeepCCG to use a log conditional marginal likelihood loss to update the representation, which can be seen as a new type of replay. To perform the update to the classifier and representation, DeepCCG maintains a fixed number of examples in memory and so a key part of DeepCCG is selecting what examples to store, choosing the subset that minimises the KL divergence between the true posterior and the posterior induced by the subset. We demonstrate the performance of DeepCCG on a range of settings, including those with overlapping tasks which thus far have been under-explored. In the experiments, DeepCCG outperforms all other methods, evidencing its potential.

Building cross-model intelligence that can understand charts and communicate the salient information hidden behind them is an appealing challenge in the vision and language(V+L) community. The capability to uncover the underlined table data of chart figures is a critical key to automatic chart understanding. We introduce ChartT5, a V+L model that learns how to interpret table information from chart images via cross-modal pre-training on plot table pairs. Specifically, we propose two novel pre-training objectives: Masked Header Prediction (MHP) and Masked Value Prediction (MVP) to facilitate the model with different skills to interpret the table information. We have conducted extensive experiments on chart question answering and chart summarization to verify the effectiveness of the proposed pre-training strategies. In particular, on the ChartQA benchmark, our ChartT5 outperforms the state-of-the-art non-pretraining methods by over 8% performance gains.

This text presents an introduction to an emerging paradigm in control of dynamical systems and differentiable reinforcement learning called online nonstochastic control. The new approach applies techniques from online convex optimization and convex relaxations to obtain new methods with provable guarantees for classical settings in optimal and robust control. The primary distinction between online nonstochastic control and other frameworks is the objective. In optimal control, robust control, and other control methodologies that assume stochastic noise, the goal is to perform comparably to an offline optimal strategy. In online nonstochastic control, both the cost functions as well as the perturbations from the assumed dynamical model are chosen by an adversary. Thus the optimal policy is not defined a priori. Rather, the target is to attain low regret against the best policy in hindsight from a benchmark class of policies. This objective suggests the use of the decision making framework of online convex optimization as an algorithmic methodology. The resulting methods are based on iterative mathematical optimization algorithms, and are accompanied by finite-time regret and computational complexity guarantees.

An essential element of K-12 AI literacy is educating learners about the ethical and societal implications of AI systems. Previous work in AI ethics literacy have developed curriculum and classroom activities that engage learners in reflecting on the ethical implications of AI systems and developing responsible AI. There is little work in using game-based learning methods in AI literacy. Games are known to be compelling media to teach children about complex STEM concepts. In this work, we developed a competitive card game for middle and high school students called "AI Audit" where they play as AI start-up founders building novel AI-powered technology. Players can challenge other players with potential harms of their technology or defend their own businesses by features that mitigate these harms. The game mechanics reward systems that are ethically developed or that take steps to mitigate potential harms. In this paper, we present the game design, teacher resources for classroom deployment and early playtesting results. We discuss our reflections about using games as teaching tools for AI literacy in K-12 classrooms.

Motivated by the intuitive understanding humans have about the space of possible interactions, and the ease with which they can generalize this understanding to previously unseen scenes, we develop an approach for learning visual affordances for guiding robot exploration. Given an input image of a scene, we infer a distribution over plausible future states that can be achieved via interactions with it. We use a Transformer-based model to learn a conditional distribution in the latent embedding space of a VQ-VAE and show that these models can be trained using large-scale and diverse passive data, and that the learned models exhibit compositional generalization to diverse objects beyond the training distribution. We show how the trained affordance model can be used for guiding exploration by acting as a goal-sampling distribution, during visual goal-conditioned policy learning in robotic manipulation.