12 citations · 12 across the 5 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
DASH: Fast, Valid Counterfactuals for Deep Networks via Batched Directional Search
Shraman Pal, Gabriel Medeiros, Clayton Escouper das Chagas +1
Counterfactual explanations are most useful when they can be generated with low latency, remain close to the factual input, and satisfy input-domain, categorical, and actionability…
cs.LG2026
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
Shraman Pal, Can Li
Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these proble…