REVIEW 4 cited by
A short note on learning discrete distributions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
The goal of this short note is to provide simple proofs for the "folklore facts" on the sample complexity of learning a discrete probability distribution over a known domain of size $k$ to various distances $\varepsilon$, with error probability $\delta$.
Forward citations
Cited by 4 Pith papers
-
Learning Distributions from Multiple Data Providers
PAC learning from restricted conditional samples is possible iff the co-occurrence graph is complete, with optimal sample complexity ranging continuously from ~n/ε² to n²/ε² by query-family structure.
-
Gradient-free stochastic optimization of derivatives under strong convexity
The minimax optimal rate for minimizing the k-th derivative of a Hölder function from noisy zero-order queries is N^{-(β-1)/(β+k)}, achieved by a kernel-based projected stochastic gradient algorithm.
-
SPAM Tolerance for Pauli Error Estimation
An entanglement-free algorithm estimates Pauli error rates with exp(O(n^{1/3})) channel uses, tolerating strong state-preparation and measurement noise.
-
Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques
The paper claims that in-context learning with finite example sets can approximate supervised fine-tuning in transformers, but the proof assumes the very approximation it sets out to establish.
Discussion (0). Continue with ORCID to comment.