Search Results for author:
Found 8 papers, 4 papers with code
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs.
Human-level play in the game of Diplomacy by combining language models with strategic reasoning
Despite much progress in training AI systems to imitate human language, building agents that use language to communicate intentionally with humans in interactive environments remains a major challenge.
Learning in Stackelberg Games with Non-myopic Agents
Although learning in Stackelberg games is well-understood when the agent is myopic, dealing with non-myopic agents poses additional complications.
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
Leveraging this observation, we propose a Train-Convexify-Train (TCT) procedure to sidestep this issue: first, learn features using off-the-shelf methods (e. g., FedAvg); then, optimize a convexified problem obtained from the network's empirical neural tangent kernel approximation.
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
On the other hand, we find that the classical GCV estimator (Craven and Wahba, 1978) accurately predicts generalization risk even in such overparameterized settings.
Predicting Out-of-Distribution Error with the Projection Norm
Projection Norm first uses model predictions to pseudo-label test samples and then trains a new model on the pseudo-labels.
Learning Equilibria in Matching Markets from Bandit Feedback
Large-scale, two-sided matching platforms must find market outcomes that align with user preferences while simultaneously learning these preferences from data.
Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
They provide robustness-consistency trade-offs for a variety of online problems.
