Skip to main content
Search

# Distributionally Robust Optimization

4 related articles

Subscribe to updates
  1. arXiv

    Robust Q-learning drops the generative model: one Markovian trajectory suffices, with near-minimax sample complexity

    For robust Markov decision processes with total-variation uncertainty sets, a model-free asynchronous Q-learning algorithm relies only on a single Markovian trajectory from a behavior policy, without a generative model or queries to arbitrary state-action pairs. It estimates robust Bellman updates through a resampled surrogate next state, uses $|S||A|$ space, and reaches entrywise ϵ\epsilon accuracy with a sample complexity of order ∣S∣∣A∣tmixϵ2μmin⁡\frac{|S||A| t_{\mathrm{mix}}}{\epsilon^2 \mu_{\min}} up to logarithmic factors, carrying the extra factor inherent to Q-learning.

    Chinese University of Hong Kong
    Yuchen Jiao（First author）
    Q-learningSample ComplexityDistributionally Robust Optimization
  2. arXiv

    Multi-source learning stops guarding every worst-case mix: pulling adversarial weights back to a reference keeps low-rank representations stable across time

    In multi-source learning the deployment population's source composition is unknown, and optimizing against the worst source mixture can be overly conservative. PILLAR regularizes adversarial source weights toward a user-specified reference distribution while learning a shared low-rank matrix, solving the resulting nonconvex-concave problem by bifactored gradient descent with mirror ascent, with linear convergence and an error bound that separates low-rank estimation from adversarial reweighting. Simulations and an electronic health record study of suicide-attempt risk show improved worst-source and transported predictive accuracy.

    Harvard University
    Keyao Zhan（First author）
    PILLARDistributionally Robust OptimizationLow-Rank Matrix EstimationBGDMAElectronic Health Record
  3. arXiv

    DRQ minimizes worst-case reconstruction loss on a fixed quantization grid, improving perplexity and downstream accuracy for LLMs quantized by six PTQ methods without adding inference overhead

    The authors show that lower reconstruction loss on calibration data in weight-only PTQ does not guarantee better model performance and can even degrade it on the same calibration data; they propose DRQ, which minimizes worst-case reconstruction loss over a constrained set of input activation distributions by updating only the integer codes of quantized weights while keeping bit width, grouping, scales, and zero points fixed, improving perplexity and average task accuracy across six PTQ methods and both dense and MoE models without adding inference overhead.

    Shanghai University of Finance and EconomicsShenzhen Research Institute of Big DataChinese Academy of SciencesImperial College London
    Yanlong Zhao（First author）
    Distributionally Robust QuantizationPost-Training QuantizationDistributionally Robust OptimizationMixture-of-Experts
  4. arXiv

    FairRSFM evaluates three remote sensing foundation models by biome group and finds aggregate metrics mask ecological performance gaps

    The authors introduce FairRSFM, which maps georeferenced samples from four remote sensing downstream datasets (m-EuroSAT, m-BigEarthNet, m-SA-Crop-Type, and MMEarth20K) to 14 terrestrial biome classes consolidated into six macro-groups, and evaluates Prithvi-EO-2.0, SatMAE, and DOFA under a unified frozen-backbone protocol across three random seeds, showing that aggregate metrics consistently mask biome-dependent disparities, for example Prithvi-EO-2.0 reaching high overall macro-F1 on m-EuroSAT while its worst-group score is markedly lower, and compares BOLP, DBR, and GroupDRO as mitigation baselines whose effectiveness is model- and task-dependent.

    Indian Institute of Technology BombayIndian Institute of Science Education and Research, Bhopal
    Md Aminur Hossain（First author）
    Linear ProbingDistributionally Robust OptimizationBenchmark Construction and EvaluationFoundation Models

You’re all caught up