SearcharxivSearch

arXiv subjects

Nariman Farsad

Publications and source records attributed to Nariman Farsad.

At least 19 recordsLinked to original sources

Multi-User Diversity Scaling in Heavy-Tailed Fading

Classical multi-user diversity theory predicts that throughput over Rayleigh fading channels grows as $\log_2\!\log_2 K$. In this work, we demonstrate a fundamental shift in this scaling law under heavy-tailed composite fading. Specifically, under Fisher--Snedecor $\mathcal{F}$ composite fading, the channel power acquires a regularly varying upper tail, shifting extreme-value statistics from the Gumbel to the Fr\'echet domain. We prove that the maximum SINR among $K$ users scales polynomially as $K^{1/m_s}$, where $m_s$ is the shadowing severity parameter, leading to an ergodic capacity scaling of $\frac{1}{m_s}\log_2 K$. Crucially, this scaling persists in interference-limited Poisson networks, where aggregate co-channel interference alters the scaling constant but not the exponent. This polynomial gain is most relevant in severe-to-moderate shadowing ($m_s \le 3$), as encountered in body-area networks, vehicular/industrial IoT, and dense indoor environments, where Fr\'echet asymptotics overtake industry-standard lognormal models at practical user counts. Finally, we establish the conditions necessary to harvest this gain (showing that proportional-fair scheduling under quasi-static shadowing reverts to Gumbel scaling) and validate all analytical findings through Monte Carlo simulations, including MIMO random beamforming.

cs.IT

Meta-World+: An Improved, Standardized, RL Benchmark

Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which inhibit a fair comparison of algorithms. This work strives to disambiguate these results from the literature, while also leveraging the past versions of Meta-World to provide insights into multi-task and meta-reinforcement learning benchmark design. Through this process we release a new open-source version of Meta-World (https://github.com/Farama-Foundation/Metaworld/) that has full reproducibility of past results, is more technically ergonomic, and gives users more control over the tasks that are included in a task set.

cs.AI

Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics

Natural language is often the easiest and most convenient modality for humans to specify tasks for robots. However, learning to ground language to behavior typically requires impractical amounts of diverse, language-annotated demonstrations collected on each target robot. In this work, we aim to separate the problem of what to accomplish from how to accomplish it, as the former can benefit from substantial amounts of external observation-only data, and only the latter depends on a specific robot embodiment. To this end, we propose Video-Language Critic, a reward model that can be trained on readily available cross-embodiment data using contrastive learning and a temporal ranking objective, and use it to score behavior traces from a separate actor. When trained on Open X-Embodiment data, our reward model enables 2x more sample-efficient policy training on Meta-World tasks than a sparse reward only, despite a significant domain gap. Using in-domain data but in a challenging task generalization setting on Meta-World, we further demonstrate more sample-efficient training than is possible with prior language-conditioned reward models that are either trained with binary classification, use static images, or do not leverage the temporal information present in video data.

cs.RO

Multi-Task Reinforcement Learning Enables Parameter Scaling

Multi-task reinforcement learning (MTRL) aims to endow a single agent with the ability to perform well on multiple tasks. Recent works have focused on developing novel sophisticated architectures to improve performance, often resulting in larger models; it is unclear, however, whether the performance gains are a consequence of the architecture design itself or the extra parameters. We argue that gains are mostly due to scale by demonstrating that naively scaling up a simple MTRL baseline to match parameter counts outperforms the more sophisticated architectures, and these gains benefit most from scaling the critic over the actor. Additionally, we explore the training stability advantages that come with task diversity, demonstrating that increasing the number of tasks can help mitigate plasticity loss. Our findings suggest that MTRL's simultaneous training across multiple tasks provides a natural framework for beneficial parameter scaling in reinforcement learning, challenging the need for complex architectural innovations.

cs.LG

A Perspective on Neural Capacity Estimation: Viability and Reliability

Recently, several methods have been proposed for estimating the mutual information from sample data using deep neural networks. These estimators ar referred to as neural mutual information estimation (NMIE)s. NMIEs differ from other approaches as they are data-driven estimators. As such, they have the potential to perform well on a large class of capacity problems. In order to test the performance across various NMIEs, it is desirable to establish a benchmark encompassing the different challenges of capacity estimation. This is the objective of this paper. In particular, we consider three scenarios for benchmarking:i the classic AWGN channel, ii channels continuous inputs optical intensity and peak-power constrained AWGN channel iii channels with a discrete output, i.e., Poisson channel. We also consider the extension to the multi-terminal case with iv the AWGN and optical MAC models. We argue that benchmarking a certain NMIE across these four scenarios provides a substantive test of performance. In this paper we study the performance of mutual information neural estimator (MINE), smoothed mutual information lower-bound estimator (SMILE), and directed information neural estimator (DINE). and provide insights on the performance of other methods as well. To summarize our benchmarking results, MINE provides the most reliable performance.

cs.IT

Deep Unfolding for Iterative Stripe Noise Removal

The non-uniform photoelectric response of infrared imaging systems results in fixed-pattern stripe noise being superimposed on infrared images, which severely reduces image quality. As the applications of degraded infrared images are limited, it is crucial to effectively preserve original details. Existing image destriping methods struggle to concurrently remove all stripe noise artifacts, preserve image details and structures, and balance real-time performance. In this paper we propose a novel algorithm for destriping degraded images, which takes advantage of neighbouring column signal correlation to remove independent column stripe noise. This is achieved through an iterative deep unfolding algorithm where the estimated noise of one network iteration is used as input to the next iteration. This progression substantially reduces the search space of possible function approximations, allowing for efficient training on larger datasets. The proposed method allows for a more precise estimation of stripe noise to preserve scene details more accurately. Extensive experimental results demonstrate that the proposed model outperforms existing destriping methods on artificially corrupted images on both quantitative and qualitative assessments.

eess.IV

MICAL: Mutual Information-Based CNN-Aided Learned Factor Graphs for Seizure Detection from EEG Signals

We develop a hybrid model-based data-driven seizure detection algorithm called Mutual Information-based CNNAided Learned factor graphs (MICAL) for detection of eclectic seizures from EEG signals. Our proposed method contains three main components: a neural mutual information (MI) estimator, 1D convolutional neural network (CNN), and factor graph inference. Since during seizure the electrical activity in one or more regions in the brain becomes correlated, we use neural MI estimators to measure inter-channel statistical dependence. We also design a 1D CNN to extract additional features from raw EEG signals. Since the soft estimates obtained as the combined features from the neural MI estimator and the CNN do not capture the temporal correlation between different EEG blocks, we use them not as estimates of the seizure state, but to compute the function nodes of a factor graph. The resulting factor graphs allows structured inference which exploits the temporal correlation for further improving the detection performance. On public CHB-MIT database, We conduct three evaluation approaches using the public CHB-MIT database, including 6-fold leave-four-patients-out cross-validation, all patient training; and per patient training. Our evaluations systematically demonstrate the impact of each element in MICAL through a complete ablation study and measuring six performance metrics. It is shown that the proposed method obtains state-of-the-art performance specifically in 6-fold leave-four-patients-out cross-validation and all patient training, demonstrating a superior generalizability.

eess.SP

Neural Capacity Estimators: How Reliable Are They?

Recently, several methods have been proposed for estimating the mutual information from sample data using deep neural networks and without the knowing closed form distribution of the data. This class of estimators is referred to as neural mutual information estimators. Although very promising, such techniques have yet to be rigorously bench-marked so as to establish their efficacy, ease of implementation, and stability for capacity estimation which is joint maximization frame-work. In this paper, we compare the different techniques proposed in the literature for estimating capacity and provide a practitioner perspective on their effectiveness. In particular, we study the performance of mutual information neural estimator (MINE), smoothed mutual information lower-bound estimator (SMILE), and directed information neural estimator (DINE) and provide insights on InfoNCE. We evaluated these algorithms in terms of their ability to learn the input distributions that are capacity approaching for the AWGN channel, the optical intensity channel, and peak power-constrained AWGN channel. For both scenarios, we provide insightful comments on various aspects of the training process, such as stability, sensitivity to initialization.

cs.IT

CNN-Aided Factor Graphs with Estimated Mutual Information Features for Seizure Detection

We propose a convolutional neural network (CNN) aided factor graphs assisted by mutual information features estimated by a neural network for seizure detection. Specifically, we use neural mutual information estimation to evaluate the correlation between different electroencephalogram (EEG) channels as features. We then use a 1D-CNN to extract extra features from the EEG signals and use both features to estimate the probability of a seizure event.~Finally, learned factor graphs are employed to capture the temporal correlation in the signal. Both sets of features from the neural mutual estimation and the 1D-CNN are used to learn the factor nodes. We show that the proposed method achieves state-of-the-art performance using 6-fold leave-four-patients-out cross-validation.

eess.SP

Learned Factor Graphs for Inference from Stationary Time Sequences

The design of methods for inference from time sequences has traditionally relied on statistical models that describe the relation between a latent desired sequence and the observed one. A broad family of model-based algorithms have been derived to carry out inference at controllable complexity using recursive computations over the factor graph representing the underlying distribution. An alternative model-agnostic approach utilizes machine learning (ML) methods. Here we propose a framework that combines model-based algorithms and data-driven ML tools for stationary time sequences. In the proposed approach, neural networks are developed to separately learn specific components of a factor graph describing the distribution of the time sequence, rather than the complete inference task. By exploiting stationary properties of this distribution, the resulting approach can be applied to sequences of varying temporal duration. Learned factor graph can be realized using compact neural networks that are trainable using small training sets, or alternatively, be used to improve upon existing deep inference systems. We present an inference algorithm based on learned stationary factor graphs, which learns to implement the sum-product scheme from labeled data, and can be applied to sequences of different lengths. Our experimental results demonstrate the ability of the proposed learned factor graphs to learn to carry out accurate inference from small training sets for sleep stage detection using the Sleep-EDF dataset, as well as for symbol detection in digital communications with unknown channels.

cs.LG

Efficient Epileptic Seizure Detection Using CNN-Aided Factor Graphs

We propose a computationally efficient algorithm for seizure detection. Instead of using a purely data-driven approach, we develop a hybrid model-based/data-driven method, combining convolutional neural networks with factor graph inference. On the CHB-MIT dataset, we demonstrate that the proposed method can generalize well in a 6 fold leave-4-patientout evaluation. Moreover, it is shown that our algorithm can achieve as much as 5% absolute improvement in performance compared to previous data-driven methods. This is achieved while the computational complexity of the proposed technique is a fraction of the complexity of prior work, making it suitable for real-time seizure detection.

eess.SP

Neural Computation of Capacity Region of Memoryless Multiple Access Channels

This paper provides a numerical framework for computing the achievable rate region of memoryless multiple access channel (MAC) with a continuous alphabet from data. In particular, we use recent results on variational lower bounds on mutual information and KL-divergence to compute the boundaries of the rate region of MAC using a set of functions parameterized by neural networks. Our method relies on a variational lower bound on KL-divergence and an upper bound on KL-divergence based on the f-divergence inequalities. Unlike previous work, which computes an estimate on mutual information, which is neither a lower nor an upper bound, our method estimates a lower bound on mutual information. Our numerical results show that the proposed method provides tighter estimates compared to the MINE-based estimator at large SNRs while being computationally more efficient. Finally, we apply the proposed method to the optical intensity MAC and obtain a new achievable rate boundary tighter than prior works.

cs.IT

Model-Based Machine Learning for Communications

We present an introduction to model-based machine learning for communication systems. We begin by reviewing existing strategies for combining model-based algorithms and machine learning from a high level perspective, and compare them to the conventional deep learning approach which utilizes established deep neural network (DNN) architectures trained in an end-to-end manner. Then, we focus on symbol detection, which is one of the fundamental tasks of communication receivers. We show how the different strategies of conventional deep architectures, deep unfolding, and DNN-aided hybrid algorithms, can be applied to this problem. The last two approaches constitute a middle ground between purely model-based and solely DNN-based receivers. By focusing on this specific task, we highlight the advantages and drawbacks of each strategy, and present guidelines to facilitate the design of future model-based deep learning systems for communications.

eess.SP

A Survey on Modulation Techniques in Molecular Communication via Diffusion

This survey paper focuses on modulation aspects of molecular communication, an emerging field focused on building biologically-inspired systems that embed data within chemical signals. The primary challenges in designing these systems are how to encode and modulate information onto chemical signals, and how to design a receiver that can detect and decode the information from the corrupted chemical signal observed at the destination. In this paper, we focus on modulation design for molecular communication via diffusion systems. In these systems, chemical signals are transported using diffusion, possibly assisted by flow, from the transmitter to the receiver. This tutorial presents recent advancements in modulation and demodulation schemes for molecular communication via diffusion. We compare five different modulation types: concentration-based, type-based, timing-based, spatial, and higher-order modulation techniques. The end-to-end system designs for each modulation scheme are presented. In addition, the key metrics used in the literature to evaluate the performance of these techniques are also presented. Finally, we provide a numerical bit error rate comparison of prominent modulation techniques using analytical models. We close the tutorial with a discussion of key open issues and future research directions for design of molecular communication via diffusion systems.

cs.ET

Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes

Reed-Muller (RM) codes are one of the oldest families of codes. Recently, a recursive projection aggregation (RPA) decoder has been proposed, which achieves a performance that is close to the maximum likelihood decoder for short-length RM codes. One of its main drawbacks, however, is the large amount of computations needed. In this paper, we devise a new algorithm to lower the computational budget while keeping a performance close to that of the RPA decoder. The proposed approach consists of multiple sparse RPAs that are generated by performing only a selection of projections in each sparsified decoder. In the end, a cyclic redundancy check (CRC) is used to decide between output codewords. Simulation results show that our proposed approach reduces the RPA decoder's computations up to $80\%$ with negligible performance loss.

cs.IT

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

Symbol detection plays an important role in the implementation of digital receivers. In this work, we propose ViterbiNet, which is a data-driven symbol detector that does not require channel state information (CSI). ViterbiNet is obtained by integrating deep neural networks (DNNs) into the Viterbi algorithm. We identify the specific parts of the Viterbi algorithm that are channel-model-based, and design a DNN to implement only those computations, leaving the rest of the algorithm structure intact. We then propose a meta-learning based approach to train ViterbiNet online based on recent decisions, allowing the receiver to track dynamic channel conditions without requiring new training samples for every coherence block. Our numerical evaluations demonstrate that the performance of ViterbiNet, which is ignorant of the CSI, approaches that of the CSI-based Viterbi algorithm, and is capable of tracking time-varying channels without needing instantaneous CSI or additional training data. Moreover, unlike conventional Viterbi detection, ViterbiNet is robust to CSI uncertainty, and it can be reliably implemented in complex channel models with constrained computational burden. More broadly, our results demonstrate the conceptual benefit of designing communication systems to that integrate DNNs into established algorithms.

cs.LG

Capacities and Optimal Input Distributions for Particle-Intensity Channels

This work introduces the particle-intensity channel (PIC) as a model for molecular communication systems and characterizes the capacity limits as well as properties of the optimal (capacity-achieving) input distributions for such channels. In the PIC, the transmitter encodes information, in symbols of a given duration, based on the probability of particle release, and the receiver detects and decodes the message based on the number of particles detected during the symbol interval. In this channel, the transmitter may be unable to control precisely the probability of particle release, and the receiver may not detect all the particles that arrive. We model this channel using a generalization of the binomial channel and show that the capacity-achieving input distribution for this channel always has mass points at probabilities of particle release of zero and one. To find the capacity-achieving input distributions, we develop an efficient algorithm we call dynamic assignment Blahut-Arimoto (DAB). For diffusive particle transport, we also derive the conditions under which the input with two mass points is capacity-achieving.

cs.IT

Two-Way Molecular Communications

For nano-scale communications, there must be cooperation and simultaneous communication between nano devices. To this end, in this paper we investigate two-way (a.k.a. bi-directional) molecular communications between nano devices. If different types of molecules are used for the communication links, the two-way system eliminates the need to consider self-interference. However, in many systems, it is not feasible to use a different type of molecule for each communication link. Thus, we propose a two-way molecular communication system that uses a single type of molecule. We develop a channel model for this system and use it to analyze the proposed system's bit error rate, throughput, and self-interference. Moreover, we propose analog- and digital- self-interference cancellation techniques. The enhancement of link-level performance using these techniques is confirmed with both numerical and analytical results.

cs.ET