Ryan Wiley PRO

rdubwiley

5

·

AI & ML interests

None yet

Recent Activity

updated a Space about 4 hours ago

rdubwiley/repro-understanding-catastrophic-forgetting-in-lora-via-mean-field-attention-dynamics

published a Space about 4 hours ago

rdubwiley/repro-understanding-catastrophic-forgetting-in-lora-via-mean-field-attention-dynamics

published a bucket about 4 hours ago

rdubwiley/repro-understanding-catastrophic-forgetting-in-lora-via-mean-field-attention-dynamics-artifacts

View all activity

Organizations

rdubwiley 's buckets 93

rdubwiley/repro-understanding-catastrophic-forgetting-in-lora-via-mean-field-attention-dynamics-artifacts

rdubwiley/repro-incentivizing-truthfulness-and-collaborative-fairness-in-bayesian-learning-artifacts

rdubwiley/repro-chain-of-thought-reasoning-in-the-wild-is-not-always-faithful-artifacts

rdubwiley/repro-reward-redistribution-for-cvar-mdps-using-a-bellman-operator-on-l-infinity-artifacts

rdubwiley/repro-adalina-adaptive-linear-approximation-for-the-shapley-value-and-beyond-artifacts

rdubwiley/repro-reinforcement-learning-for-reachability-guaranteeing-asymptotic-optimality-artifacts

rdubwiley/repro-safesearch-automated-red-teaming-of-llm-based-search-agents-artifacts

rdubwiley/repro-two-parameter-flows-for-learning-population-dynamics-of-physical-systems-artifacts

rdubwiley/repro-beyond-relu-bifurcation-oversmoothing-and-topological-priors-artifacts

rdubwiley/repro-exact-functional-anova-decomposition-for-categorical-inputs-models-artifacts

rdubwiley/repro-singular-vectors-of-attention-heads-align-with-features-artifacts

rdubwiley/repro-balanced-lora-removing-parameter-invariance-to-accelerate-convergence-artifacts

rdubwiley/repro-hierarchical-successor-representation-for-robust-transfer-artifacts

rdubwiley/repro-domain-transfer-becomes-identifiable-via-a-single-alignment-artifacts

rdubwiley/repro-global-convergence-of-adaptive-sensing-for-principal-eigenvector-estimation-artifacts

rdubwiley/repro-equilibrium-pricing-in-oligopolistic-data-markets-artifacts

rdubwiley/repro-refined-analysis-of-entropy-regularized-actor-critic-artifacts

rdubwiley/repro-is-data-shapley-not-better-than-random-in-data-selection-ask-nash-artifacts

rdubwiley/repro-accuracy-first-r-nyi-differential-privacy-and-post-processing-immunity-artifacts

rdubwiley/repro-are-your-agents-upward-deceivers-artifacts

rdubwiley/repro-large-language-models-develop-novel-social-biases-through-adaptive-exploration-artifacts

rdubwiley/repro-set-preserving-calibration-from-conformal-p-values-to-e-values-artifacts

rdubwiley/repro-mean-shift-pca-by-knockoff-mean-artifacts

rdubwiley/repro-no-free-lunch-non-asymptotic-analysis-of-prediction-powered-inference-artifacts

rdubwiley/repro-gaussian-mean-field-variational-inference-can-overestimate-predictive-variance-artifacts

rdubwiley/conformal-risk-averse-decision-making-with-action-repro-artifacts

rdubwiley/near-optimal-and-efficient-first-order-algorithm-repro-artifacts

rdubwiley/revisiting-ml-training-under-fully-homomorphic-repro-artifacts

rdubwiley/emergent-analogical-reasoning-in-transformers-repro-artifacts

rdubwiley/a-theoretical-framework-for-statistical-repro-artifacts