AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

CoNSoLe: Convex Neural Symbolic Learning

Haoran Li, Yang Weng, Hanghang Tong

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 2 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use double-convex deep Q-learning instead of traditional deep Q-learning (ablation)CoNSoLe · Syn1 and Syn2E_c (%)Improved
Add ε-greedy exploration to deep Q-learning (ablation)CoNSoLe · Syn1 and Syn2E_c (%)Improved
Add a static symbolic constraint (ablation)CoNSoLe · Syn2E_c (%)Improved
Add a dynamic symbolic constraint (ablation)CoNSoLe · Syn1E_c (%)Improved
Use LoCaL gradient-based coefficient estimation instead of BFGS (ablation)CoNSoLe · Syn1 and Syn2E_c (%)No clear effect
Use CoNSoLe rather than the benchmark methodsSymbolic regression · Pow and Masequation-learning performanceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy