Derives ODE limits of Adam-DA showing that first- and second-order momentum parameters reverse their convergence roles in zero-sum games compared to minimization, validated on GAN experiments.
hub
International conference on machine learning , pages=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Participatory provenance auditing of Canada's AI strategy consultation shows official AI summaries exclude 15-17% of participants more than random baselines, with 33-88% exclusion for dissent clusters.
A discrete-time constant flux condition on the heat equation forces the domain to be a ball under suitable regularity.
Provides the first systematic generalization analysis via algorithmic stability for single-timescale and two-timescale stochastic gradient descent-ascent in bilevel minimax problems.
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
DCMA uses conditional generative models to recover and simulate interventional outcome distributions for distributional causal mediation effects, with derived error bounds.
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
MetaTrans improves unsupervised video domain adaptation performance by separating and subtracting spatial and temporal divergences via a dedicated module and a minimal two-term loss objective.
citing papers explorer
-
Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
Derives ODE limits of Adam-DA showing that first- and second-order momentum parameters reverse their convergence roles in zero-sum games compared to minimization, validated on GAN experiments.
-
Participatory provenance as representational auditing for AI-mediated public consultation
Participatory provenance auditing of Canada's AI strategy consultation shows official AI summaries exclude 15-17% of participants more than random baselines, with 33-88% exclusion for dissent clusters.
-
A discrete-time overdetermined problem for the heat equation
A discrete-time constant flux condition on the heat equation forces the domain to be a ball under suitable regularity.
-
On the Stability and Generalization of First-order Bilevel Minimax Optimization
Provides the first systematic generalization analysis via algorithmic stability for single-timescale and two-timescale stochastic gradient descent-ascent in bilevel minimax problems.
-
Training Deep Learning Models with Norm-Constrained LMOs
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
-
Diffusion Posterior Sampling for General Noisy Inverse Problems
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
-
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
-
Distributional Causal Mediation via Conditional Generative Modeling
DCMA uses conditional generative models to recover and simulate interventional outcome distributions for distributional causal mediation effects, with derived error bounds.
-
Rectified Flow: A Marginal Preserving Approach to Optimal Transport
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
-
Return of Frustratingly Easy Unsupervised Video Domain Adaptation
MetaTrans improves unsupervised video domain adaptation performance by separating and subtracting spatial and temporal divergences via a dedicated module and a minimal two-term loss objective.
- Implicit Neural Optimal Transport via Fixed-Point Optimization