Experiments on three LLMs across coding, math, and reasoning benchmarks demonstrate that ReD substantially reduces the required attempts, tokens, and USD cost to reach a desired coverage, while also offering an efficient way to measure inference power-laws.
S. Meir, Tommer D. Keidar, Noam Levi et al.· arXiv.org· 3 citations
This study establishes DUA-D2C as a theoretically grounded and effective approach to combating overfitting in modern deep learning, analytically demonstrating how dynamic parameter fusion reduces model variance.
The framework thereby makes preference aggregation an explicit and statistically analyzable design choice rather than an implicit consequence of pooling human feedback, and produces a single policy with explicit collective-welfare guarantees.
Hui-Ying Zhong, Tian-Wei Gao, Z. Wu et al.· 30 citations· ⚡4
A general procedure for evaluating epistemic potency in discrete settings is given, and it is shown that ID-pruned experiments are combinatorially inert, yielding a super-exponential reduction in the number of subsets evaluated.
It is proved that in-context learning extends further to data generation: frozen transformers can simulate iterative generative samplers from in-context samples, and it is proved that transformers can approximate an energy-based sampler.
Arman Adibi, Alireza Jafari, Mohammad Ghavamzadeh et al.· 0 citations
In simulations, DLNAMs generally outperformed DLNM comparators, including penalized and treed variants, in recovering known response functions, with lower bias, stronger boundary recovery, and better-calibrated cumulative intervals; gains were largest for more demanding functions.
Calle Helmersson, Shivangi Pandey, Leonardo Olivetti et al.· 0 citations
The optimal transport (OT) map provides a geometric transformation for aligning probability distributions and has become a useful tool in machine learning. However, existing estimators of the OT map still exhibit a gap between sharp statistical guarantees and practical parametric estimation based on stable training obj...
Kunwoong Kim, Insung Kong, Yongdai Kim· 0 citations
This work proposes the use of normalizing flow models to reconstruct calibration-affected weak signals by leveraging the statistical invariance of the target signals and assuming minimal initial suppression, and effectively recovers the lost signal components.
It is shown that vanilla SGDA, without any modification to its update rule, can converge under heavy-tailed noise in both nonconvex-strongly-concave (NC-SC) and nonconvex-concave (NC-C) settings, establishing the first convergence guarantees for SGDA in these regimes.
Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We connect Amari's Bayesian duality to a convex duality of Bayes' rule. Using this connection, we present a generalization of Amari's Bayesian du...
Mohammad Emtiyaz Khan, Thomas M\"ollenhoff· 0 citations
B-spline regression constitutes a widely used framework for nonparametric modeling. The performance of this methodology depends on specifying the number and placement of changepoints, known as knots, prior to the estimation process. Such knot sequence determines the dimension of the B-spline basis used to represent the...
Neural Low-Degree Filtering (Neural LoFi) is introduced, a stylized limit of gradient-based training in which hierarchical feature learning becomes an explicit iterative spectral procedure and provides a mathematically explicit framework for studying multi-layer feature learning beyond the lazy regime.
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Is your company’s AI sovereign? A practical guide for CIOs on AI vendor lock-in, EU Data Act switching, cloud sovereignty, and testing your exit plan before you need it. The post Sovereignty Is the Option to Leave appeared first on GPT-Lab.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
