Hypothesis selection is a fundamental problem in learning theory and statistics. Given a dataset and a finite set of candidate distributions, the goal is to select a distribution that matches the data as well as possible. More specifically, suppose that we have sample access to an unknown distribution P over a domain X that we know is well-approximated by one of a class of n distributions (a.k.a.

Reinforcement learning (RL) algorithms face two distinct challenges: learning effective representations of past and present observations, and determining how actions influence future returns. Both challenges involve modeling long-term dependencies. The Transformer architecture has been very successful to solve problems that involve long-term dependencies, including in the RL domain. However, the underlying reason for the strong performance of Transformer-based RL methods remains unclear: is it because they learn effective memory, or because they perform effective credit assignment? After introducing formal definitions of memory length and credit assignment length, we design simple configurable tasks to measure these distinct quantities. Our empirical results reveal that Transformers can enhance the memory capability of RL algorithms, scaling up to tasks that require memorizing observations 1500 steps ago. However, Transformers do not improve long-term credit assignment. In summary, our results provide an explanation for the success of Transformers in RL, while also highlighting an important area for future research and benchmark design.

In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especially when labeled data is scarce. However, most current SSL methods rely on heuristics or predefined rules for generating pseudo-labels and leveraging unlabeled data. They are limited to exploiting loss functions and regularization methods within the standard norm. In this paper, we propose a novel Reinforcement Learning (RL) Guided SSL method, RLGSSL, that formulates SSL as a one-armed bandit problem and deploys an innovative RL loss based on weighted reward to adaptively guide the learning process of the prediction model. RLGSSL incorporates a carefully designed reward function that balances the use of labeled and unlabeled data to enhance generalization performance. A semi-supervised teacher-student framework is further deployed to increase the learning stability. We demonstrate the effectiveness of RLGSSL through extensive experiments on several benchmark datasets and show that our approach achieves consistent superior performance compared to state-of-the-art SSL methods.

Diffusion models, a specific type of generative model, have achieved unprecedented performance in recent years and consistently produce high-quality synthetic samples. A critical prerequisite for their notable success lies in the presence of a substantial number of training samples, which can be impractical in real-world applications due to high collection costs or associated risks. Consequently, various finetuning and regularization approaches have been proposed to transfer knowledge from existing pre-trained models to specific target domains with limited data. This paper introduces the Transfer Guided Diffusion Process (TGDP), a novel approach distinct from conventional finetuning and regularization methods. We prove that the optimal diffusion model for the target domain integrates pre-trained diffusion models on the source domain with additional guidance from a domain classifier. We further extend TGDP to a conditional version for modeling the joint distribution of data and its corresponding labels, together with two additional regularization terms to enhance the model performance.

In recent years, the design of specialized machine learning architectures for structured data has received a surge of interest. Of particular interest are architectures for data domains with inherent symmetries, such as permutation-invariance in graphs and sets, translation-invariance in images, and other symmetries that arise from fundamental laws of physics in scientific data.

As governments and corporations adopt deep learning systems to collect and analyze user-generated audio data, concerns about security and privacy naturally emerge in areas such as automatic speaker recognition. While audio adversarial examples offer one route to mislead or evade these invasive systems, they are typically crafted through time-intensive offline optimization, limiting their usefulness in streaming contexts. Inspired by architectures for audio-toaudio tasks such as denoising and speech enhancement, we propose a neural network model capable of adversarially modifying a user's audio stream in realtime. Our model learns to apply a time-varying finite impulse response (FIR) filter to outgoing audio, allowing for effective and inconspicuous perturbations on a small fixed delay suitable for streaming tasks. We demonstrate our model is highly effective at de-identifying user speech from speaker recognition and able to transfer to an unseen recognition system. We conduct a perceptual study and find that our method produces perturbations significantly less perceptible than baseline anonymization methods, when controlling for effectiveness. Finally, we provide an implementation of our model capable of running in real-time on a single CPU thread.