2 citations · 2 across the 8 of their papers we have counts for
11 papers
Task-Sufficient Contraction: Source Selection for Machine Information Interfaces
Joss Armstrong
A declared task can sometimes certify a reduced source before a downstream encoder, codebook, rate, distortion target, or optimizer is chosen. This paper studies when one such redu…
Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution
Joss Armstrong
Repeated training on model-generated data can degrade later models. One possible response is to use provenance when deciding which generated examples to reuse. We test both how rel…
Task-Oriented Quantization for Quadratic Scheduling: Centroid Water-Filling and Power-Diagram Encoders
Joss Armstrong
We distinguish two regimes in task-oriented quantization with a known deterministic oracle action. For an unconstrained interior oracle and a smooth strongly concave utility, quant…
Privacy-Preserving Intent Fulfilment and Assurance for 6G RAN
Joss Armstrong
Intent-based network management automates 6G service lifecycles, but existing fulfilment and assurance approaches require traffic inspection, per-flow tracking, or vendor-internal…
Designed-Source Reductions and a Dual-Purpose Feasibility Band for Semantic Rate-Distortion
Joss Armstrong
The joint rate-distortion framework of Stavrou and Kountouris (IEEE Transactions on Communications 2023) characterises dual-fidelity tradeoffs for semantic communication on stochas…
Demo: BeGREEN Intelligence Plane for AI-driven Energy Efficient O-RAN management
M. Catalan-Cid, D. Reiss, G. Castellanos +1
Cellular networks management is being enhanced by O-RAN architecture and AI/ML solutions, enabling automated intelligent control loops for RAN optimization across various use cases…
Multi-Resolution Attribution from Adaptive Routing State
Joss Armstrong
Adaptive hierarchical systems accumulate routing state as they learn which components to select. We show that this state already defines a coherent attribution over the hierarchy.…
Information Requirements for Service Allocation and Aggregate Verification
Joss Armstrong
A service system may use the same categories to assign standard allocations and to check whether each service is fulfilled. Finer categories can match individual needs more closely…
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
Joss Armstrong
When a coordinator compares answers from heterogeneous foundation models, self-reported confidence may have different meanings across responders and changing workloads. This paper…
Hierarchical Learning Automata Without a Shared Reinforcement Signal: Recovering the Environment Response From Action-Probability Changes
Joss Armstrong
A hierarchy of learning automata in the sense of Thathachar and Ramakrishnan activates one root-to-leaf path per round, and every automaton on that path updates from the environmen…
Source-Side Sufficiency for the Information Bottleneck: Exact Reduction and Finite-Block Equivalence
Joss Armstrong
The input side of the Information Bottleneck may contain task-irrelevant variation that still costs rate. We identify this cost exactly. Let T be a source and C a relevance variabl…