Neural compression is currently dominated by Nonlinear Transform Coding (NTC), which maps data to real-valued latents via continuous transforms. Despite its success, NTC suffers from train-test mismatch due to non-differentiable quantization, a ``smoothness bias" inherent in continuous transforms that precludes optimality for certain sources, and a loss of ``shaping gain" due to the complexity of including high-dimensional vector quantization. We propose SoftBinary Coding (SBC), an end-to-end learning paradigm that bypasses these limitations by using a stochastic binary latent space. In the spirit of vector quantization, SBC employs discrete representations and compresses them through a novel fast binary channel simulation scheme, for which we provide a proof of rate optimality. Experimental gains on information-theoretic sources provide both theoretical and practical closure to NTC's limitations, establishing discrete binary structures as a viable path toward reaching optimal rate--distortion bounds. Surprisingly, SBC also achieves state-of-the-art performance on vector quantization of i.i.d. sources, exceeding Trellis Coded Quantization of the Gaussian source.
In this paper, we propose a compression framework for weighted graphs in which the graph topology is transmitted losslessly and edge weights are compressed lossily. A challenge in the lossy compression of edge weights is that the underlying relationships between edges are ambiguo…
We study the use of runlength-limited (RLL) block codes in bit-interleaved coded modulation (BICM) systems. In this setting, the RLL code acts as the symbol mapper, whose assignment between input bits and RLL symbols is critical for performance. In this work, we aim at optimizing…
Physical artificial intelligence (AI) systems involve distributed sensing agents with embedded AI models that must coordinate to perceive, reason, and act in networked environments. Transmitting raw sensor data incurs significant communication overhead, latency, and redundancy. W…
In standard federated learning systems, the parameter server broadcasts the global model to the participating devices in every iteration. Motivated by the temporal correlation between consecutive global models, differential coding can be applied to global model dissemination to r…
Future wireless networks are expected to support networked artificial intelligence (AI) services, where multiple devices transmit learned features to an edge server for distributed inference. This setting calls for task-oriented physical-layer optimization, where wireless transmi…
Wireless physical neural networks (WPNNs) embed neural computation directly into analog hardware, offering lower energy consumption and latency than conventional digital implementations. In this paper, we propose a deep WPNN in which nonlinear activations are realized by a multi-…