Designing robust and efficient codes for reliable communication in noisy environments is a key challenge. Recent advancements show that deep learning-based channel codes can outperform traditional handcrafted ones in certain scenarios. Despite recent advancements, most state-of-the-art codes are trained using the binary cross-entropy (BCE) loss, LBCE, which aims to optimize bit error rate (BER) but is less effective at minimizing block error rate (BLER) – a critical metric for avoiding costly re-transmissions in wireless systems. To address this limitation, we first apply several recently-proposed BLER-specific loss functions to train channel autoencoders, i.e., to design both the neural encoder and the matched neural decoder. Our results show that the application of such loss functions improves the design of autoencoders, compared to the conventional BCE loss, especially when BLER is the performance metric of interest. Next, we introduce a novel loss function, called the adaptively-scaled norm (ASN) loss, LASN, which dynamically adjusts penalties based on the error rates across the bit positions, making it more effective for BLER minimization. Compared to existing methods, the proposed loss function promotes a lower variance for the contribution from different bit positions while still emphasizing more on the bit positions with higher chances of error. Using a two-step process of pre-training and fine-tuning, we show that LASNoutperforms LBCEand the existing BLER-minimizing loss functions across various communication channels.

In steganography, selecting an optimal cover image—referred to as cover selection—is pivotal for effective message concealment. Traditional methods have typically employed exhaustive searches to identify images that conform to specific perceptual or complexity metrics. However, the relationship between these metrics and the actual message hiding efficacy of an image is unclear, often yielding less-than-ideal steganographic outcomes. Inspired by recent advancements in generative models, we introduce a novel cover selection framework, which involves optimizing within the latent space of pretrained generative models to identify the most suitable cover images, distinguishing itself from traditional exhaustive search methods. Our method shows significant advantages in message recovery and image quality. We also conduct an information-theoretic analysis of the generated cover images, revealing that message hiding predominantly occurs in low-variance pixels, reflecting the waterfilling algorithm's principles in parallel Gaussian channels.

A two-user interference channel is a canonical model for multiple one-to-one communications, where two transmitters wish to communicate with their receivers via a shared medium, examples of which include pairs of base stations and handsets near the cell boundary that suffer from interference. Practical codes and the fundamental limit of communications are unknown for interference channels as mathematical analysis becomes intractable. Hence, simple heuristic coding schemes are used in practice to mitigate interference, e.g., time division, treating interference as noise, and successive interference cancellation. These schemes are nearly optimal for extreme cases: when interference is strong or weak. However, there is no optimality guarantee for channels with moderate interference. Here we combine deep learning and network information theory to overcome the limitation on the tractability of analysis and construct finite-blocklength coding schemes for channels with various interference levels. We show that carefully designed and trained neural codes using network information theoretic insight can achieve several orders of reliability improvement for channels with moderate interference. Furthermore, we present the interpretation of the learned codes based on the codeword distance and the Centered Kernel Alignment (CKA) analysis.

A critical aspect of reliable communication involves the design of codes that allow transmissions to be robustly and computationally efficiently decoded under noisy conditions. Advances in the design of reliable codes have been driven by coding theory and have been sporadic. Recently, it is shown that channel codes that are comparable to modern codes can be learned solely via deep learning. In particular, Turbo Autoencoder (TurboAE), introduced by Jiang et al., is shown to achieve the reliability of Turbo codes for Additive White Gaussian Noise channels.In this paper, we focus on applying the idea of TurboAE to various practical channels, such as fading channels and chirp noise channels. We introduce TurboAE-TI, a novel neural architecture that combines TurboAE with a trainable interleaver design. We develop a carefully-designed training procedure and a novel interleaver penalty function that are crucial in learning the interleaver and TurboAE jointly. We demonstrate that TurboAE-TI outperforms TurboAE and LTE Turbo codes for several channels of interest. We also provide interpretation analysis to better understand TurboAE-TI.

The two-user interference channel is a model for multi one-to-one communications, where two transmitters wish to communicate with their corresponding receivers via a shared wireless medium. Two most common and simple coding schemes are Time Division (TD) and Treating Interference as Noise (TIN). Interestingly, it is shown that there exists an asymptotic scheme, called Han-Kobayashi scheme, that performs better than TD and TIN. However, Han-Kobayashi scheme has impractically high complexity and is designed for asymptotic settings, which leads to a gap between information theory and practice. In this paper, we focus on designing practical codes for interference channels. As it is challenging to analytically design practical codes with feasible complexity, we apply deep learning to learn codes for interference channels. We demonstrate that DeepIC, a convolutional neural network-based code with an iterative decoder, outperforms TD and TIN by a noticeable margin for two-user Additive White Gaussian Noise channels with moderate amount of interference.

In this paper, we develop a framework for an autoencoder based transmission strategy for achieving distributed interference alignment and optimal power allocation in a multiuser interference channel. The users in the interference channel have access to the local channel state information only. We compare the explicit schemes, such as MaxSINR [1], against the autoencoder schemes. We find that the MaxSINR schemes outperform the autoencoder networks which are either jointly or distributively trained from scratch. However, we find that the autoencoders which are pretrained with the beamforming vectors and the power allocation obtained from the explicit schemes outperform the explicit schemes when the interference gets stronger. The explicit schemes perform well as they are effective in choosing the set of users which are to be suppressed. The pretrained autoencoders benefit from this initialization, and also from the fact that end to end training can improve their performance even further. We showcase our performance comparison results for 5 user interference channels with different levels of interference.