Posters

Scalable Kernel Inverse Optimization (KIO) efficiently learns unknown objective functions from data using kernel methods and a novel Sequential Selection Optimization (SSO) algorithm, enabling applica…

This paper reveals significant privacy gaps in shuffling-based DP-SGD, proposes a scalable Poisson subsampling method, and demonstrates its superior utility for private model training.

sDBSCAN: Blazing-fast density-based clustering for massive datasets using random projections!

Scalable MAPPO-L: Decentralized training with local interactions ensures safe, high-reward multi-agent systems, even with limited communication.

FOCALBO, a hierarchical Bayesian optimization algorithm using focalized sparse Gaussian processes, efficiently tackles high-dimensional problems with massive datasets, achieving state-of-the-art perfo…

SCAFFLSA tames heterogeneity in federated learning, achieving logarithmic communication complexity and linear sample complexity.

SaulLM-54B & SaulLM-141B achieve state-of-the-art performance on legal tasks by scaling up model size, employing a specialized instruction-following protocol, and aligning model outputs with human pre…

Satformer: a novel neural network accurately estimates satellite network traffic using an adaptive sparse spatio-temporal attention mechanism, outperforming existing methods.

SARAD: A novel anomaly detection approach for multivariate time series leverages spatial information and association reduction patterns to achieve state-of-the-art performance.

SAND, a novel transformer network variant, smoothly imputes sparse and noisy functional data by leveraging self-attention on derivatives, outperforming existing methods.

Reconstructing geometry from minimal Euclidean distance samples: A novel algorithm achieves state-of-the-art data efficiency with theoretical guarantees.

Accelerated Primal-Dual Natural Policy Gradient (PD-ANPG) algorithm achieves a theoretical lower bound sample complexity for solving general parameterized CMDPs, improving state-of-the-art by a factor…

Boost Bayesian Optimization’s efficiency by leveraging known invariances in objective functions for faster, more effective solutions.

Agnostic boosting gets a major efficiency upgrade! A new algorithm leverages sample reuse to drastically reduce the data needed for accurate learning, closing the gap with computationally expensive al…

ConFrag, a novel approach to noisy label regression, leverages contrastive fragmentation and neighborhood agreement to select clean samples, significantly outperforming state-of-the-art baselines on s…

Efficiently learn causal graphs from limited interventions using a novel Bayesian algorithm that outperforms existing methods and requires fewer experiments.

First finite-sample analysis of interventional causal representation learning shows that surprisingly few samples suffice for accurate graph and latent variable recovery.

Neural networks enhance algorithm selection in branch-and-cut, significantly reducing tree sizes and improving efficiency for mixed-integer optimization, as proven by rigorous theoretical bounds and e…

This paper presents a computationally efficient algorithm for robustly learning Gaussian single-index models under adversarial label noise, achieving near-optimal sample complexity.

SampDetox uses diffusion models to purify poisoned machine learning samples by strategically adding noise to eliminate backdoors without compromising data integrity.