🔄 In a Training Loop

Abdullah Mujeeb Khawaja

amkkk

·

https://navigatingnoise.substack.com/

AI & ML interests

None yet

Recent Activity

liked a Space about 13 hours ago

ICML-2026-agent-repro/challenge

liked a model about 13 hours ago

AxiomicLabs/GPT-X2.5-135M

liked a model 1 day ago

0xSero/Gemma-4-21B

View all activity

Organizations

amkkk 's buckets 131

amkkk/repro-towards-understanding-adam-convergence-on-highly-degenerate-polynomials-artifacts

amkkk/repro-box-thirding-anytime-best-arm-identification-under-insufficient-sampling-artifacts

amkkk/densest-k-diag-loading-vq-artifacts

amkkk/repro-lloyd-hartigan-kmeans-artifacts

amkkk/repro-a-tight-theory-of-error-feedback-algorithms-in-distributed-optimization-artifacts

amkkk/repro-lion-optimizer-artifacts

amkkk/repro-improved-convergence-analysis-of-topology-dependence-in-decentralized-sgd-artifacts

amkkk/repro-commit-to-the-bit-reactive-reinforcement-learning-done-right-artifacts

amkkk/repro-logarithmic-switching-regret-for-online-convex-optimization-artifacts

amkkk/repro-subset-opt-artifacts

amkkk/repro-complexity-bounds-for-dirichlet-process-slice-samplers-artifacts

amkkk/repro-instance-specific-approximation-ratios-for-correlation-clustering-and-max-cut-artifacts

amkkk/repro-identifying-dependent-components-from-multi-domain-linear-mixtures-artifacts

amkkk/yZAo4TPqhE-artifacts

amkkk/repro-varde-34cmbsgpT5-artifacts

amkkk/repro-general-analysis-of-lmo-based-optimizers-beyond-bounded-variance-artifacts

amkkk/btt-repro-Yq66fTPjHn-artifacts

amkkk/repro-asymmetric-conformal-prediction-with-penalized-kernel-sum-of-squares-artifacts

amkkk/repro-desirable-effort-fairness-and-optimality-trade-offs-in-strategic-learning-artifacts

amkkk/repro-sgk-artifacts

amkkk/repro-understanding-the-gaps-in-satisficing-bandits-artifacts

amkkk/repro-subset-optimization-artifacts

amkkk/repro-fc2fb-artifacts

amkkk/repro-near-optimal-private-linear-regression-via-iterative-hessian-mixing-artifacts

amkkk/repro-regret-minimization-with-a-crowd-of-awakening-experts-artifacts

amkkk/repro-signal-strength-estimation-in-logistic-regression-using-data-splitting-artifacts

amkkk/repro-near-optimal-regret-for-kl-regularized-multi-armed-bandits-artifacts

amkkk/repro-minimum-distance-summaries-for-robust-neural-posterior-estimation-artifacts

amkkk/repro-unveiling-the-structure-of-do-calculus-reasoning-via-derivation-graphs-artifacts

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