Entity · technique

Ensemble Diversity Optimization

techniqueactiveprovisionalensemble-diversity-optimization-6d18a98b·1 events·first seen 2d ago

Aliases: Ensemble Diversity Optimization

Co-occurring entities

More like this (12)

distributed optimization Greedy Ensemble Selection distributionally robust optimization Local Diversity Divergence Regularized Policy Optimization Pair Opt-dist Bayesian Multiobjective Optimization Denoising Diffusion Policy Optimization Mixture of Efficient Experts Direct Preference Optimization (DPO)Bayesian Optimization Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Recent events (1)

4arXiv · cs.CL·2d ago·source ↗

Ensemble Diversity Optimization (EDO) improves calibration on subjective NLP tasks

Researchers introduce Ensemble Diversity Optimization (EDO), a differentiable framework that jointly optimizes ensemble weights, effective cardinality, and calibration for subjective NLP tasks where annotator disagreement is systematic. EDO uses Gumbel-Softmax relaxation and a signed diversity regularizer to prevent ensemble collapse and navigate the utility-calibration trade-off. Experiments on four subjective text-classification benchmarks show 40-78% reductions in cross-entropy versus baselines while maintaining competitive F1 and better alignment with annotator distributions.

Evaluation and Benchmarking Alignment and RLHF HS-Brexit ArMIS MD-Agreement +2 more