Adversarially robust (1+ε)-approximate F_p estimation for all p∈[0,2] in polylog space is achieved via implicit isometric embeddings into Hilbert space and regularized kernel regression, plus a weak equivalence theorem between oblivious sketching and robust streaming.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
There is a sharp threshold at interaction degree 3 where classical sampling from depth-1 QAOA becomes hard enough to collapse the polynomial hierarchy, contrasting with efficient simulation at degree 2 for logarithmic depth.
POOL is a new RL algorithm that adds privacy protection in continuous spaces with one-sided feedback and achieves sample complexity matching known non-private lower bounds.
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
citing papers explorer
-
Adversarial Robustness for Small Frequency Moments and a Weak Equivalence Theorem for Turnstile Streams
Adversarially robust (1+ε)-approximate F_p estimation for all p∈[0,2] in polylog space is achieved via implicit isometric embeddings into Hilbert space and regularized kernel regression, plus a weak equivalence theorem between oblivious sketching and robust streaming.
-
A sharp interaction-degree threshold for simulating QAOA
There is a sharp threshold at interaction degree 3 where classical sampling from depth-1 QAOA becomes hard enough to collapse the polynomial hierarchy, contrasting with efficient simulation at degree 2 for logarithmic depth.
-
Privacy Preserving Reinforcement Learning with One-Sided Feedback
POOL is a new RL algorithm that adds privacy protection in continuous spaces with one-sided feedback and achieves sample complexity matching known non-private lower bounds.
-
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
-
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.