THEORIA / RESEARCH CATALOG

Open problems
in foundations of AI/ML.

Find your next research direction. Explore conjectures and open questions through their models, mathematical targets and connections.

Theory & computationMathematical models & guarantees
119open problems

Explore with /next-steps ↗ or /attack slash commands

A source-linked collection of theoretical open problems. Explore challenges in AI safety, learning theory, transformers, world models, optimization, memory and inference. Each entry gives a precise research target, assumptions and known progress. Open status is provisional; broader programs explicitly need a framework. Sources & methodology ↗

Seed catalog · Browse the bundled collection. Search matches words; Supabase mode uses ranked full-text search.

START EXPLORING
SubjectStatistical inference
TypeAll types
ReviewAll entries

Choose multiple options. Results match any selected value within each filter.

12 problems

Inverse RL & imitation · Statistical inference · AI safety & alignmentOpen question

Can Behavior Reveal the Reward?

Matching an expert's actions need not reveal why they act that way. Reliable reward learning must describe what behavior can and cannot tell us.

Editorially scoped

3 sources · Framework needs definitionRead
AI safety & alignment · Verification & proof search · Statistical inferenceOpen question

Can Finite Audits Certify an Adaptive Conversation?

Multi-turn certificates rely on worst-case transition and persistence properties, while practical audits observe only a finite selection of conversations. Efficiency payoff: Spend audits on safety-relevant states and transitions instead of repeatedly testing whole conversations without a coverage argument.

Editorially scoped

3 sources · Framework needs definitionRead
Statistical inference · Embeddings & representations · Optimization & optimizersOpen question

Can Neural Networks Recover Interaction Graphs?

Neural networks can represent complex interactions parsimoniously. Turning their learned features into a trustworthy scientific interaction graph requires more than a good fit.

Editorially scoped

3 sources · Framework needs definitionRead
Statistical inference · Statistical learning theory · Data-efficient learningOpen question

How Many Correlations Are Enough?

The information that determines a model need not be information an algorithm can use efficiently. Higher-order observations may trade measurement cost for computational tractability.

Editorially scoped

3 sources · Specified modelRead
Statistical inference · Statistical learning theoryOpen question

Learning Interactions from Fluctuations

Observed correlations reflect both interactions and the dynamics used to observe them. Inference near slow or critical regimes must account for both.

Editorially scoped

6 sources · Framework needs definitionRead
Information retrieval · Statistical inferenceOpen question

Learning Relevance from Biased Feedback

Search engines learn from behavior they helped create. Without identifying the exposure mechanism, more clicks can reinforce an incorrect ranking.

Editorially scoped

3 sources · Framework needs definitionRead
Statistical inference · Statistical learning theoryOpen question

Logistic Regression at the Separability Threshold

Near separability, tiny changes in regularization or sample size can have large effects on coefficients and confidence even in this simple convex model. Efficiency payoff: Guide finite-data regularization and stopping choices near a sharp statistical transition instead of relying on unstable asymptotic extrapolations.

Editorially scoped

4 sources · Framework needs definitionRead
Statistical inference · Embeddings & representationsOpen question

Revealing Hidden Interactions

A learned interaction graph can confuse direct dependence with unobserved causes. Hidden-spin models make this ambiguity mathematically concrete.

Editorially scoped

3 sources · Framework needs definitionRead
Data-efficient learning · Statistical inferenceOpen question

The Best Data for a Fixed Budget

More data is not always better value. A learner should discover which sources provide the most useful evidence for the target task.

Editorially scoped

3 sources · Framework needs definitionRead
Statistical inference · Statistical learning theoryOpen question

The True Sample Cost of Distribution Testing

Two distributions with equally large support can require very different amounts of data to distinguish from a reference. A sharp instance-dependent bound would capture that difference.

Editorially scoped

2 sources · Specified modelRead
Bayesian learning · Statistical inferenceOpen question

When Can Bayesian Confidence Be Trusted?

A precise posterior can still be confidently wrong. Useful Bayesian learning needs uncertainty that remains informative when both the model and inference are approximate.

Editorially scoped

3 sources · Framework needs definitionRead
Symbolic regression & equation discovery · Statistical inferenceOpen question

Which PDE Can Coarse Measurements Reveal?

A compact equation fitted to coarse observations may describe only the discretization or unresolved fluctuations, rather than the underlying constitutive law. Efficiency payoff: Identify when a small reusable PDE model can replace expensive field-level prediction without requiring unnecessarily fine observations.

Editorially scoped

3 sources · Framework needs definitionRead