Next-token prediction with cross-entropy loss is the objective of choice in sequence and language modeling. Despite its widespread use, there is a lack of theoretical analysis regarding the generalization of models trained using this objective. In this work, we provide an analysis of empirical risk minimization for sequential inputs generated by order-$k$ Markov chains. Assuming bounded and Lipschitz logit functions, our results show that in-sample prediction error decays optimally with the number of tokens, whereas out-of-sample error incurs an additional term related to the mixing properties of the Markov chain. These rates depend on the statistical complexity of the hypothesis class and can lead to generalization errors that do not scale exponentially with the order of the Markov chain—unlike classical $k$-gram estimators. Finally, we discuss the possibility of achieving generalization rates independent of mixing.

This paper addresses the problem of long-context linear system identification, where the state $x_t$ of the system at time $t$ depends linearly on previous states $x_s$ over a fixed context window of length $p$. We establish a sample complexity bound that matches the _i.i.d._ parametric rate, up to logarithmic factors for a broad class of systems, extending previous work that considered only first-order dependencies. Our findings reveal a ``learning-without-mixing'' phenomenon, indicating that learning long-context linear autoregressive models is not hindered by slow mixing properties potentially associated with extended context windows. Additionally, we extend these results to _(i)_ shared low-rank feature representations, where rank-regularized estimators improve rates with respect to dimensionality, and _(ii)_ misspecified context lengths in strictly stable systems, where shorter contexts offer statistical advantages.

Due to its empirical success in few-shot classification and reinforcement learning, meta-learning has recently received significant interest. Meta-learning methods leverage data from previous tasks to learn a new task in a sample-efficient manner. In particular, model-agnostic methods look for initialization points from which gradient descent quickly adapts to any new task. Although it has been empirically suggested that such methods perform well by learning shared representations during pretraining, there is limited theoretical evidence of such behavior. More importantly, it has not been shown that these methods still learn a shared structure, despite architectural misspecifications. In this direction, this work shows, in the limit of an infinite number of tasks, that first-order ANIL with a linear two-layer network architecture successfully learns linear shared representations. This result even holds with _overparametrization_; having a width larger than the dimension of the shared representations results in an asymptotically low-rank solution. The learned solution then yields a good adaptation performance on any new task after a single gradient step. Overall, this illustrates how well model-agnostic methods such as first-order ANIL can learn shared representations.

Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of semantic editing operations, such as zoom or rotation. The discovery of such directions is often done in a supervised or semi-supervised manner and requires manual annotations which limits their use in practice. In comparison, unsupervised discovery allows finding subtle directions that are difficult to detect a priori. In this work, we propose a contrastive learning-based approach to discover semantic directions in the latent space of pre-trained GANs in a self-supervised manner. Our approach finds semantically meaningful dimensions compatible with state-of-the-art methods.

Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often limited to a fixed set of hard-coded transformations. Recently, several works proposed to use generative models for generating semantically meaningful perturbations to train a classifier. However, because accurate encoding and decoding are critical, these methods, which use architectures that approximate the latent-variable inference, remained limited to pilot studies on small datasets.Exploiting the exactly reversible encoder-decoder structure of normalizing flows, we perform on-manifold perturbations in the latent space to define fully unsupervised data augmentations. We demonstrate that such perturbations match the performance of advanced data augmentation techniques—reaching 96.6% test accuracy for CIFAR10 using ResNet-18 and outperform existing methods, particularly in low data regimes—yielding 10–25% relative improvement of test accuracy from classical training. We find that our latent adversarial perturbations adaptive to the classifier throughout its training are most effective, yielding the first test accuracy improvement results on real-world datasets—CIFAR-10/100—via latent-space perturbations.