Related papers: Duet: efficient and scalable hybriD neUral rElatio…

Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus on merging all…

In this work, we show that for linearly constrained optimization problems the primal-dual hybrid gradient algorithm, analyzed by Chambolle and Pock [3], can be written as an entirely primal algorithm. This allows us to prove convergence of…

Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential drift in the feature…

Unsupervised efficient domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, while maintaining low storage cost and high retrieval efficiency. However, existing methods typically…

Online monitoring user cardinalities (or degrees) in graph streams is fundamental for many applications. For example in a bipartite graph representing user-website visiting activities, user cardinalities (the number of distinct visited…

Concept drift in learning and classification occurs when the statistical properties of either the data features or target change over time; evidence of drift has appeared in search data, medical research, malware, web data, and video. Drift…

SQL queries, with the AND, OR, and NOT operators, constitute a broad class of highly used queries. Thus, their cardinality estimation is important for query optimization. In addition, a query planner requires the set-theoretic cardinality…

Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accuracy at the cost of multi-step autoregressive inference,…

The demise of Moore's Law has led to the rise of hardware acceleration. However, the focus on accelerating stable algorithms in their entirety neglects the abundant fine-grained acceleration opportunities available in broader domains and…

Current directed graph embedding methods build upon undirected techniques but often inadequately capture directed edge information, leading to challenges such as: (1) Suboptimal representations for nodes with low in/out-degrees, due to the…

We present a novel deep learning approach to approximate the solution of large, sparse, symmetric, positive-definite linear systems of equations. These systems arise from many problems in applied science, e.g., in numerical methods for…

Imbalance in classification tasks is commonly quantified by the cardinalities of examples across classes. This, however, disregards the presence of redundant examples and inherent differences in the learning difficulties of classes.…

Efficient sampling of satisfying formulas for circuit satisfiability (CircuitSAT), a well-known NP-complete problem, is essential in modern front-end applications for thorough testing and verification of digital circuits. Generating such…

Bayesian inference with nested sampling requires a likelihood-restricted prior sampling method, which draws samples from the prior distribution that exceed a likelihood threshold. For high-dimensional problems, Markov Chain Monte Carlo…

Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications. It aims to improve the generalization ability of pre-trained models when deployed on resource-constrained…

This paper presents new methods to estimate the cardinalities of data sets recorded by HyperLogLog sketches. A theoretically motivated extension to the original estimator is presented that eliminates the bias for small and large…

Causal inference in modern largescale systems faces growing challenges, including highdimensional covariates, multi-valued treatments, massive observational (OBS) data, and limited randomized controlled trial (RCT) samples due to cost…

In this paper, we study the problem of deriving fast and accurate classification algorithms with uncertainty quantification. Gaussian process classification provides a principled approach, but the corresponding computational burden is…

Motivated by problems in contact mechanics, we propose a duality approach for computing approximations and associated a posteriori error bounds to solutions of variational inequalities of the first kind. The proposed approach improves upon…

Deep neural networks often produce overconfident predictions, undermining their reliability in safety-critical applications. This miscalibration is further exacerbated under distribution shift, where test data deviates from the training…