Search papers, labs, and topics across Lattice.
Department of Computer Science University of Manchester Manchester, UK, Department of Computer Science Aalto University Espoo, Finland, ELLIS Institute Finland Helsinki, Finland
3
0
5
Stop assuming a single utility function: modeling preferences as a mixture of archetypes unlocks better Bayesian optimization in complex, many-objective spaces.
Even with imperfect proxies for latent confounders, robust predictors can still be uniquely identified across domains, provided those domains are sufficiently diverse in their latent structure.
Causal embeddings can rescue meta-learning from negative transfer in out-of-distribution scenarios, even with noisy expert feedback.
