α-TCAV replaces TCAV's hard indicator with a tunable smooth function to create a unified probabilistic framework with lower variance and guidance for parameter choice or Bayes-optimal scoring.
Journal of Machine Learning Research , year =
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
unclear 1representative citing papers
High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
LAPRAS uses predictions to answer likely queries with the offline Matrix Mechanism and paces residual budget for unpredicted queries via unbiased stopping-time estimation from the first few unexpected arrivals, achieving near-offline utility when overlap is high.
GAME is a convex estimator using overlapping nuclear-norm penalties on subgroup submatrices for low-rank matrix completion with known overlapping groups, providing finite-sample guarantees on reconstruction error and subgroup subspace recovery.
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
OP-Mix is an on-policy data mixing method that uses low-rank adapter interpolation to find near-optimal data mixtures throughout language model training with reduced compute.
The SLE-MUV model produces a continuous convex analytical Pareto frontier for portfolios under volatility uncertainty, outperforming mean-variance optimization in risk-adjusted returns on US and A-share market data.
citing papers explorer
-
$\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
α-TCAV replaces TCAV's hard indicator with a tunable smooth function to create a unified probabilistic framework with lower variance and guidance for parameter choice or Bayes-optimal scoring.
-
Unveiling High-Probability Generalization in Decentralized SGD
High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
-
LAPRAS : Learning-Augmented PRivate Answering for linear query Streams
LAPRAS uses predictions to answer likely queries with the offline Matrix Mechanism and paces residual budget for unpredicted queries via unbiased stopping-time estimation from the first few unexpected arrivals, achieving near-offline utility when overlap is high.
-
Group-Aware Matrix Estimation and Latent Subspace Recovery
GAME is a convex estimator using overlapping nuclear-norm penalties on subgroup submatrices for low-rank matrix completion with known overlapping groups, providing finite-sample guarantees on reconstruction error and subgroup subspace recovery.
-
Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
-
Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time
OP-Mix is an on-policy data mixing method that uses low-rank adapter interpolation to find near-optimal data mixtures throughout language model training with reduced compute.
-
Pareto frontier of portfolio investment under volatility uncertainty and short-sale constraints market
The SLE-MUV model produces a continuous convex analytical Pareto frontier for portfolios under volatility uncertainty, outperforming mean-variance optimization in risk-adjusted returns on US and A-share market data.