Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A potential solution is data pruning, which retains only high-quality data based on a score function (human or machine feedback). Previous work Feng et al. (2024) analyzed models trained on synthetic data as sample size increases. We extend this by using random matrix theory to derive the performance of a binary classifier trained on a mix of real and pruned synthetic data in a high dimensional setting. Our findings identify conditions where synthetic data could improve performance, focusing on the quality of the generative model and verification strategy. We also show a smooth phase transition in synthetic label noise, contrasting with prior sharp behavior in infinite sample limits. Experiments with toy models and large language models validate our theoretical results.

In this paper, we analyze the sample and communication complexity of the federated linear stochastic approximation (FedLSA) algorithm. We explicitly quantify the effects of local training with agent heterogeneity. We show that the communication complexity of FedLSA scales polynomially with the inverse of the desired accuracy ϵ. To overcome this, we propose SCAFFLSA a new variant of FedLSA that uses control variates to correct for client drift, and establish its sample and communication complexities. We show that for statistically heterogeneous agents, its communication complexity scales logarithmically with the desired accuracy, similar to Scaffnew. An important finding is that, compared to the existing results for Scaffnew, the sample complexity scales with the inverse of the number of agents, a property referred to as linear speed-up. Achieving this linear speed-up requires completely new theoretical arguments. We apply the proposed method to federated temporal difference learning with linear function approximation and analyze the corresponding complexity improvements.

Driven by the compelling advantages of agility and cost-efficiency inherent in unmanned aerial vehicles (UAV s), this study introduces TANAGERS (emergenT communication for uA vs as flyinG passivE RadarS), an innovative communication-augmented multi-agent reinforcement learning algorithm (MARL) designed for the movement control of UAVs operating as flying passive radars in bistatic integrated sensing and communication scenarios. In this research, we employ the proposed MARL framework to address the sensing signal-to-noise ratio (SNR) maximization problem for targets within a given environment by leveraging signals from base stations, all while taking into account realistic communication channels between pairs of UAV s. Simulation results underscore the significant enhancement brought by our proposed algorithm in radar performance, as measured by the total achievable sensing SNR of the UAV s during their trajectory. The key strength lies in the algorithm's ability to learn a resilient communication protocol that effectively mitigates the stochastic and unreliable nature of channel links between UAV s.

This demonstration introduces SOREO, a system that explores the possibility of extending UAVs autonomy through machine learning. It brings a contribution to the following problem: Having a fleet of drones and a geographic area, how to learn the shortest paths between any point with regards to the base points for optimal and safe package delivery? Starting from a set of possible actions, a virtual design of a geographic location of interest, e.g., a city, and a reward value, SOREO is capable of learning not only how to prevent collisions with obstacles, e.g., walls and buildings, but also to find the shortest path between any two points, i.e., the base and the target. SOREO exploits based on the Q-learning algorithm.

we consider the problem of sequential change-point detection where both the change-points and the distributions before and after the change are assumed to be unknown. For this problem of primary importance in statistical and sequential learning theory, we derive a variant of the Bayesian Online Change Point Detector proposed by \cite{fearnhead2007line} which is easier to analyze than the original version while keeping its powerful message-passing algorithm. We provide a non-asymptotic analysis of the false-alarm rate and the detection delay that matches the existing lower-bound. We further provide the first explicit high-probability control of the detection delay for such approach. Experiments on synthetic and real-world data show that this proposal outperforms the state-of-art change-point detection strategy, namely the Improved Generalized Likelihood Ratio (Improved GLR) while compares favorably with the original Bayesian Online Change Point Detection strategy.

We consider the decentralized exploration problem: a set of players collaborate to identify the best arm by asynchronously interacting with the same stochastic environment. The objective is to insure privacy in the best arm identification problem between asynchronous, collaborative, and thrifty players. In the context of a digital service, we advocate that this decentralized approach allows a good balance between conflicting interests: the providers optimize their services, while protecting privacy of users and saving resources. We define the privacy level as the amount of information an adversary could infer by intercepting all the messages concerning a single user. We provide a generic algorithm DECENTRALIZED ELIMINATION, which uses any best arm identification algorithm as a subroutine. We prove that this algorithm insures privacy, with a low communication cost, and that in comparison to the lower bound of the best arm identification problem, its sample complexity suffers from a penalty depending on the inverse of the probability of the most frequent players. Then, thanks to the genericity of the approach, we extend the proposed algorithm to the non-stationary bandits. Finally, experiments illustrate and complete the analysis.

The Industrial Internet of Things (IIoT) faces multiple challenges to achieve high reliability, low-latency and low power consumption. The IEEE 802.15.4 Time-Slotted Channel Hopping (TSCH) protocol aims to address these issues by using frequency hopping to improve the transmission quality when coping with low-quality channels. However, an optimized transmission system should also try to favor the use of high-quality channels, which are unknown a priori. Hence reinforcement learning algorithms could be useful.