24 accepted papers
Federated LoRA provides a communication-efficient mechanism for fine-tuning large language models on decentralized data. In practice, however, a discrepancy between the factor-wise averaging used to preserve low rank and the mathematically correct aggregation of local updates can cause significant a…
Real-world deployment of machine learning models requires the ability to continually learn from non-stationary data while preserving prior knowledge and user privacy. Therefore, storing knowledge acquired from past data in a resource- and privacy-friendly manner is a crucial consideration in determi…
Reliable communication of data in modern wireless systems requires accurate channel state information (CSI). Sounding Reference Signal (SRS) based CSI acquisition enables the estimation of the channel between the base station and user equipment through the uplink transmission of known SRS by the use…
Motivated by high resource costs of centralized machine learning schemes as well as data privacy concerns, federated learning (FL) emerged as an efficient alternative that relies on aggregating locally trained models rather than collecting clients' potentially private data. In practice, available re…
Statistical heterogeneity of data present at client devices in a federated learning (FL) system renders the training of a global model in such systems difficult. Particularly challenging are the settings where due to communication resource constraints only a small fraction of clients can participate…
While federated learning (FL) systems often utilize quantization to battle communication and computational bottlenecks they have heretofore been limited to deploying fixed-precision quantization schemes. Meanwhile the concept of mixed-precision quantization (MPQ) where different layers of a deep lea…
Gradient inversion (GI) attacks present a threat to the privacy of clients in federated learning (FL) by aiming to enable reconstruction of the clients' data from communicated model updates. A number of such techniques attempts to accelerate data recovery by first reconstructing labels of the sample…
We study non-convex optimization problems where the data is distributed across nodes of a time-varying directed network; this describes dynamic settings in which the communication between network nodes is affected by delays or link failures. The network nodes, which can access only their local objec…
Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years, personalized federated learning (pFL) has emerged as a potential solu…
Federated learning (FL) enables distribution of machine learning workloads from the cloud to resource-limited edge devices. Unfortunately, current deep networks remain not only too compute-heavy for inference and training on edge devices, but also too large for communicating updates over bandwidth-c…
We consider the problem of decentralized optimization where a collection of agents, each having access to a local cost function, communicate over a time-varying directed network and aim to minimize the sum of those functions. In practice, the amount of information that can be exchanged between the a…
In a variety of problems, a decision-maker is unaware of the loss function associated with a task, yet it has to minimize this unknown loss in order to accomplish the task. Furthermore, the decision-maker’s task may evolve, resulting in a varying loss function. In this setting, we explore sequential…
Weak submodular optimization underpins many problems in signal processing and machine learning. For such problems, under a cardinality constraint, a simple greedy algorithm is guaranteed to find a solution with a value no worse than 1 − e <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xli…
Identifying modulation type of a received radio signal is a challenging problem encountered in many applications including radio interference mitigation and spectrum allocation. This problem is rendered challenging by the existence of a large number of modulation schemes and numerous sources of inte…
Haplotype assembly and viral quasispecies reconstruction are challenging tasks concerned with analysis of genomic mixtures using sequencing data. High-throughput sequencing technologies generate enormous amounts of short fragments (reads) which essentially oversample components of a mixture; the rep…
We propose the maximum a posteriori accelerated orthogonal least-squares (MAP-AOLS) algorithm, a novel greedy scheme for accurate reconstruction of a sparse binary signal from its compressed measurements. The algorithm leverages the distributions of the sensing matrix, signal, and noise to find a su…
Accurate path gain models are critical for coverage prediction and radio frequency (RF) planning in wireless communications. In many settings irregular terrain induces blockages and scattering making it difficult to predict the path gain. Current solutions are either computationally expensive or slo…
An evolutionary self-expressive model for clustering a collection of evolving data points that lie on a union of low-dimensional evolving subspaces is proposed. A parsimonious representation of data points at each time step is learned via a non-convex optimization framework that exploits the self-ex…
We study the problem of selecting most informative subset of a large observation set to enable accurate estimation of unknown parameters. This problem arises in a variety of settings in machine learning and signal processing including feature selection, phase retrieval, and target localization. Sinc…
We study the problem of sampling a bandlimited graph signal in the presence of noise, where the objective is to select a node subset of prescribed cardinality that minimizes the signal reconstruction mean squared error (MSE). To that end, we formulate the task at hand as the minimization of MSE subj…
We study the problem of approximating a partially observed matrix by a product of two low-rank matrices where the data as well as the factors are constrained to be binary. This computationally challenging task is motivated by the single individual haplotyping problem which attracted considerable att…
Evolutionary affinity propagation, an evolutionary clustering algorithm that groups data points by exchanging messages on a factor graph, is proposed. The algorithm promotes temporal smoothness of the clustering solutions at distinct temporal snapshots by linking variable nodes of the graph across t…
We present an algorithm, referred to as Branch and Bound Least-Squares (BBLS), for the recovery of sparse signals from a few linear combinations of their entries. Sparse signal reconstruction is readily cast as the problem of finding a sparse solution to an underdetermined system of linear equations…
In matrix decomposition problems, one often seeks to represent a data matrix by the product of two matrices - one capturing meaningful information contained in the data and the other specifying how this information is combined to generate the data matrix. We consider matrix decomposition that arises…