skwdro: a library for Wasserstein distributionally robust machine learning
We present skwdro, a Python library for training robust machine learning models. The library is based on distributionally robust optimization using Wasserstein distances, popular in optimal transport and machine learnings. The goal of the library is to make the training of robust models easier for a wide audience by proposing a wrapper for PyTorch modules, enabling model loss' robustification with minimal code changes. It comes along with scikit-learn compatible estimators for some popular objectives. The core of the implementation relies on an entropic smoothing of the original robust objective, in order to ensure maximal model flexibility. The library is available at https://github.com/iutzeler/skwdro and the documentation at https://skwdro.readthedocs.io
Vincent Florian, Waïss Azizian, Franck Iutzeler, Jérôme Malick; 27(8):1−7, 2026.
Abstract
We present skwdro, a Python library for training robust machine learning models. The library is based on distributionally robust optimization using Wasserstein distances, popular in optimal transport and machine learnings. The goal of the library is to make the training of robust models easier for a wide audience by proposing a wrapper for PyTorch modules, enabling model loss' robustification with minimal code changes. It comes along with scikit-learn compatible estimators for some popular objectives. The core of the implementation relies on an entropic smoothing of the original robust objective, in order to ensure maximal model flexibility. The library is available at https://github.com/iutzeler/skwdro and the documentation at https://skwdro.readthedocs.io
[abs][pdf][bib] [code]
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modeltrainingavailable
Exclusive | Meta Is Delaying the Rollout of Its Flagship AI Model - WSJ
<a href="https://news.google.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?oc=5" target="_blank">Exclusive | Meta Is Delaying the Rollout of Its Flagship AI Model</a> <font color="#6f6f6f">WSJ</font>
Execution-Verified Reinforcement Learning for Optimization Modeling
arXiv:2604.00442v1 Announce Type: new Abstract: Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller LLMs using costly process supervision that often overfits to a single solver API. Inspired by reinforcement learning with verifiable rewards, we propose Execution-Verified Optimization Modeling (EVOM), an execution-verified learning framework that treats a mathematical programming solver as a deterministic, interactive verifier. Given a natural-language problem and a target solver, EVOM generates solver-specific code, executes it in a sandboxed harness, and converts execution outcomes into scalar rewards, opti
Decision-Centric Design for LLM Systems
arXiv:2604.00414v1 Announce Type: new Abstract: LLM systems must make control decisions in addition to generating outputs: whether to answer, clarify, retrieve, call tools, repair, or escalate. In many current architectures, these decisions remain implicit within generation, entangling assessment and action in a single model call and making failures hard to inspect, constrain, or repair. We propose a decision-centric framework that separates decision-relevant signals from the policy that maps them to actions, turning control into an explicit and inspectable layer of the system. This separation supports attribution of failures to signal estimation, decision policy, or execution, and enables modular improvement of each component. It unifies familiar single-step settings such as routing and a
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Models
Exclusive | Meta Is Delaying the Rollout of Its Flagship AI Model - WSJ
<a href="https://news.google.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?oc=5" target="_blank">Exclusive | Meta Is Delaying the Rollout of Its Flagship AI Model</a> <font color="#6f6f6f">WSJ</font>
Execution-Verified Reinforcement Learning for Optimization Modeling
arXiv:2604.00442v1 Announce Type: new Abstract: Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller LLMs using costly process supervision that often overfits to a single solver API. Inspired by reinforcement learning with verifiable rewards, we propose Execution-Verified Optimization Modeling (EVOM), an execution-verified learning framework that treats a mathematical programming solver as a deterministic, interactive verifier. Given a natural-language problem and a target solver, EVOM generates solver-specific code, executes it in a sandboxed harness, and converts execution outcomes into scalar rewards, opti
In harmony with gpt-oss
arXiv:2604.00362v1 Announce Type: new Abstract: No one has independently reproduced OpenAI's published scores for gpt-oss-20b with tools, because the original paper discloses neither the tools nor the agent harness. We reverse-engineered the model's in-distribution tools: when prompted without tool definitions, gpt-oss still calls tools from its training distribution with high statistical confidence -- a strong prior, not a hallucination. We then built a native harmony agent harness (https://github.com/borislavmavrin/harmonyagent.git) that encodes messages in the model's native format, bypassing the lossy Chat Completions conversion. Together, these yield the first independent reproduction of OpenAI's published scores: 60.4% on SWE Verified HIGH (published 60.7%), 53.3% MEDIUM (53.2%), and
Decision-Centric Design for LLM Systems
arXiv:2604.00414v1 Announce Type: new Abstract: LLM systems must make control decisions in addition to generating outputs: whether to answer, clarify, retrieve, call tools, repair, or escalate. In many current architectures, these decisions remain implicit within generation, entangling assessment and action in a single model call and making failures hard to inspect, constrain, or repair. We propose a decision-centric framework that separates decision-relevant signals from the policy that maps them to actions, turning control into an explicit and inspectable layer of the system. This separation supports attribution of failures to signal estimation, decision policy, or execution, and enables modular improvement of each component. It unifies familiar single-step settings such as routing and a
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!