🔄 In a Training Loop

SSH PRO

ProCreations

·

https://ssh.codes

AI & ML interests

Making AI’s small, accessible, and easy to run on consumer hardware

Recent Activity

updated a Space 29 minutes ago

ProCreations/repro-asymptotically-optimal-sequential-testing-with-markovian-data

updated a Space about 1 hour ago

ProCreations/repro-finite-time-convergence-analysis-of-actor-critic-with-evolving-reward

updated a Space about 2 hours ago

ProCreations/repro-on-the-computational-complexity-of-performative-prediction

View all activity

Organizations

ProCreations 's Spaces 207

Sequential Markov testing: six-claim direct audit

Explore and collaborate on a project logbook

Actor–critic with evolving rewards: five-claim native audit

Collaborate with your coding agent via a synced logbook

Reproduction - Performative Prediction Complexity

Audit of performative-prediction complexity claims

HJ-Prox operator splitting: native-scale audit

Explore a research logbook and sync with a coding agent

Context-free transformers: native recognizer audit

Explore experiment logs with an interactive web viewer

Reproduction Learning in Bayesian Stackelberg Games

Explore and collaborate on research logbooks with an AI agent

CGP: exhaustive algorithm and rate audit

Explore and collaborate on a project logbook

Reproduction — Expressive Power of Permutation-Equivariant Weight-Space Networks

Explore experiment logs and collaborate with a coding agent

Reproduction - Sharp TV-Hellinger Inequalities

Chebyshev sharpness for Gaussian mixtures

Bandit OT: exact structural audit

Explore and sync experiment logs with an AI coding agent

Reproduction - Direct Second-Order Zero-Sum Game Solving

Explore research logs and collaborate with an agent

Repro - No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

Track and sync research reproducibility notes with an AI agent

Repro - Fine-Tuning Without Forgetting In-Context Learning

Explore and sync experiment logs with an AI agent

Reproduction - Finding Most Influential Sets

Exact top-k and selection-consistency audit

Reproduction — Approximate Reward Models for Inference-Time Scaling

Explore research logbook and sync findings with an AI agent

Reproduction - Sketch-and-Project Natural Gradient

Subsampled natural-gradient and SPRING audit

Reproduction - Benign Overfitting in Adversarial ViTs

Exact ViT theorem, softmax and released-ablation audit

Reproduction - Randomized Feasibility Methods

Adaptive randomized-feasibility convergence audit

Reproduction - Theory of Continual Learning with Gradient Descent

Explore research logbooks and sync findings with an AI agent

Reproduction - Exact Categorical Functional ANOVA

Exact dependent categorical ANOVA identity and speed audit

Reproduction Efficiently Learning Drifting Halfspaces

Browse a research logbook and view experiment details

Reproduction - Exact Unlearning in Reinforcement Learning

Explore and sync your project logbook with a coding agent

Reproduction - Delayed Momentum Aggregation

Exact DeMoA source, formula and Byzantine-majority audit

Reproduction - Doubly Regularized Robust MDPs

Exact theorem, ridge, UCB and robust-control audit