arXiv research

Study examines Fed's pandemic communication strategies.

Kalshi prediction markets forecast cryptocurrency volatility through monetary policy and inflation signals.

The paper modifies interest rate models to better fit current economic conditions.

A collaborative algorithm reduces regret in federated linear contextual bandits.

A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art resul…

D2P-Fed improves privacy and communication in federated learning.

LDP-Fed protects privacy in federated learning with neural networks.

The paper models SOFR and EFFR dynamics, reconciling diffusive and piecewise paths.

Fed-FEARE model extracts rules from multiple agencies' data securely.

Fed-TDA augments federated tabular data to improve performance and privacy.

Fed-ensemble improves FL by averaging predictions from multiple models.

We present the perceptor gradients algorithm -- a novel approach to learning symbolic representations based on the idea of decomposing an agent's policy into i) a perceptor network extracting symbols from raw observation data and ii) a task encoding program which maps the input symbols to output actions. We show that t…

Adapts MBDOE for real-time parameter estimation in complex systems.

Study improves U.S. monetary policy forecasting by integrating text and data.

This paper analyzes error feedback in compressed federated learning for non-convex optimization problems.

This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error interactions based on a reward function that signals how much the agent deviates fr…

Fed-MIWAE improves federated learning by imputing missing data.

We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to …

Federated UCBVI reduces communication costs while minimizing regret in multi-agent settings.

New method decomposes local projections to reveal historical drivers of estimates.

Unified approach to federated learning improves robustness and personalization.

Reinforcement learning and symbolic planning have both been used to build intelligent autonomous agents. Reinforcement learning relies on learning from interactions with real world, which often requires an unfeasibly large amount of experience. Symbolic planning relies on manually crafted symbolic knowledge, which may …

This paper proposes a parsimoniously time varying parameter vector autoregressive model (with exogenous variables, VARX) and studies the properties of the Lasso and adaptive Lasso as estimators of this model. The parameters of the model are assumed to follow parsimonious random walks, where parsimony stems from the ass…

A novel method for learning Bayesian network structures from decentralized data, balancing privacy and efficiency.

FEDS distills LIC model knowledge into a lightweight student for efficient compression.

Recent results on optimization and generalization properties of neural networks showed that in a simple two-layer network, the alignment of the labels to the eigenvectors of the corresponding Gram matrix determines the convergence of the optimization during training. Such analyses also provide upper bounds on the gener…

In their paper `A new algorithm for recognizing the unknot', in Geometry and Topology', 2 (1998) n. 9, 175-220, the first author and Michael Hirsch presented a then new algorithm for recognizing the unknot. The first part of the algorithm required the systematic enumeration of all discs which support a `braid foliation…

We present a novel architecture, the "stacked what-where auto-encoders" (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervised, semi-supervised and unsupervised learning without relying on sampling during training. An instantiation of SWWAE uses a convolutional ne…

Transformer learns long-term dependencies from real-world data.

Machine learning models predict housing prices using macroeconomic factors.

If the probability of default parameters (PDs) fed as input into a credit portfolio model are estimated as through-the-cycle (TTC) PDs stressed market conditions have little impact on the results of the capital calculations conducted with the model. At first glance, this is totally different if the PDs are estimated as…

Study improves privacy-preserving online prediction from experts with speed-ups.

A new federated algorithm reduces regret in X-armed bandit problems.

A new method for efficient online federated learning reduces communication overhead.

New framework provides privacy guarantees for practical federated learning.

Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep reinforcement learning methods use recurrent neural networks (RNN) to memorize pas…

Low-cost sensors improve air quality prediction accuracy significantly.

UAVs learn to collect data from IoT sensors efficiently.

This work improves fairness in federated learning by using zero-shot data augmentation.

A novel hierarchical Bayesian approach to Federated Learning reduces data exposure and improves convergence rates.

Enhances privacy in federated learning with Laplacian smoothing.

Adaptive sampling improves deep learning efficiency by focusing on informative samples.

Matrix factorization (MF) has been widely applied to collaborative filtering in recommendation systems. Its Bayesian variants can derive posterior distributions of user and item embeddings, and are more robust to sparse ratings. However, the Bayesian methods are restricted by their update rules for the posterior parame…

We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a candidate ranking problem as pairwise classification and utilizes an unsupervised neural feature ense…

Adversarial examples are slight perturbations that are designed to fool artificial neural networks when fed as an input. In this work the usability of the Fisher information for the detection of such adversarial attacks is studied. We discuss various quantities whose computation scales well with the network size, study…

FED distills ensemble predictions efficiently, improving accuracy and uncertainty.

Although highly correlated, speech and speaker recognition have been regarded as two independent tasks and studied by two communities. This is certainly not the way that people behave: we decipher both speech content and speaker traits at the same time. This paper presents a unified model to perform speech and speaker …

Computing shortest path distances between nodes lies at the heart of many graph algorithms and applications. Traditional exact methods such as breadth-first-search (BFS) do not scale up to contemporary, rapidly evolving today's massive networks. Therefore, it is required to find approximation methods to enable scalable…