Asia
Don't PourCerealintoCoffee: Differentiable TemporalLogicforTemporalActionSegmentation
We propose Differentiable Temporal Logic (DTL), a model-agnostic framework that introduces temporal constraints to deep networks. DTL treats the outputs of a network as a truth assignment of a temporal logic formula, and computes a temporal logic loss reflecting the consistency between the output and the constraints.
Test-TimeCollectivePrediction
An increasingly common setting in machine learning involves multiple parties, each with their own data, who want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents to make better predictions than they would individually, but may not be willing to release labeled data or model parameters.
Test-Time Collective Prediction
An increasingly common setting in machine learning involves multiple parties, each with their own data, who want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents to make better predictions than they would individually, but may not be willing to release labeled data or model parameters.
LocallyDifferentiallyPrivate (Contextual)Bandits Learning
Further, we extend our(ε,δ)-LDP algorithm toGeneralized Linear Bandits,which enjoysa sub-linear regret O(T3/4/ε) and is conjectured to be nearly optimal. Note that given the existingΩ(T) lower bound for DP contextual linear bandits [35], our result shows afundamental difference between LDP and DP contextual bandits learning.