Learning theory

Develop a Python library for evaluating theoretical generalization bounds in deep learning within the SIERRA team and ERC DYNASTY project. The role connects learning theory with practical neural-network evaluation through modular scientific software, empirical experiments and publications. The two-year appointment has a planned start of 1 December 2026. Flexible working and teleworking are possible.

…proof systems, locally testable codes, learning theory, harmonic analysis and additive combinatorics. The one-year project connects theoretical computer science with mathematical and quantum methods.

Develop an independent research and teaching programme in fundamental machine learning. Relevant directions include post-transformer architectures, continual learning, probabilistic and causal models, uncertainty quantification, learning theory, symbolic-statistical methods, robust learning and scientific discovery. The appointee will supervise master’s and doctoral research, develop graduate teaching in Advanced Computer Science, and contribute to undergraduate machine learning and mathematics. The employer lists salary bands of £48,337–£61,165 and £64,878–£68,817.

Katrina Ligett explores why learning theory can make pessimistic predictions even when practical systems succeed. Instead of analysing only worst-case algorithms and data, she proposes reformulating questions around properties that explain algorithmic success and instance-specific performance. Examples in generalisation and privacy illustrate how these perspectives could narrow the gap between theory and empirical practice and create new mathematical questions.

Is context nothing more than "a backdrop where learning occurs?" In learning theory there is an ongoing debate about what constitutes a context. This implies a strict division between stimuli that act as cues and those that act as context. In extinction learning, a highly context-sensitive learning process, after the cessation of a behavior, its reappearance as renewal occurs after the change of context. In this study, we tested the ability of competing stimuli to act as context in an appetitive extinction learning paradigm in pigeons (Columba livia) . The ability of each stimulus to act as a