We study decentralized learning of Nash equilibria (NE) in infinite-horizon discounted Markov games under bandit feedback, focusing on Markov $\alpha$-potential games. We develop KL-projected natural policy gradient (NPG) algorithms in two settings: an episodic setting with frozen policies during sampling and a fully o...
Dynamic cloud workflow scheduling must balance deadline satisfaction, container utilization, and energy consumption while dealing with stochastic task-execution speeds, placement-dependent communication, and coupled task and container decisions. Workflows are naturally modeled as directed acyclic graphs (DAGs), but con...
Zong-Jin Li, Shaohan Feng, Chun-Xi Yang et al.· 0 citations
Agentic serving can consume orders of magnitude more tokens than chatbot workloads, stressing both KV-cache capacity and decode-time bandwidth. Most KV-eviction methods score cached keys against representative queries drawn from the most recent tokens, assuming future attention resembles recent attention. We show that...
Taowen Tony Liu, Jeffrey T. H. Wong, Can Xiao et al.· 0 citations
Scientific machine learning methods such as physics-informed neural networks (PINNs) increasingly rely on domain decomposition for better scalability while solving partial differential equations (PDEs) over complex geometries, yet the resulting composite loss comprising residual, boundary, and interface terms is highly...
Sidharth S. Menon, Irina Tezaur, Ameya D. Jagtap· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Earth system modeling is shifting from task-specific predictors toward foundation models with general spatiotemporal representation capabilities. Although these models can jointly encode dynamic Earth fields, external forcings, and static geographic context for multistep forecasting, accurate point predictions or stati...
We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learned sequentially, and each update must preserve the endpoint mappings at previously learned samples while protecting private data. This gives each agent three roles: (i)...
Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), channel-indiscriminate multi-scale decomposition that conflates heterogeneous frequency signatures, and static multi-branch fusion that cannot adapt to market regime shifts...
Demand forecasting is critical in modern industry, offering opportunities to reduce costs and gain competitive advantage through improved inventory management. However, forecasting becomes particularly challenging for products with intermittent demand, where demand occurs infrequently and time series contain many zero...
Bayesian quantum tomography requires efficient inference while preserving a posterior fixed by the prior and Born likelihood. Learned transport provides fast amortized samples, but reward tuning can reshape the generated distribution rather than improve exploration of this fixed target. We introduce GRPO-QPS, a target-...
Yu-Feng Wang, Parivesh Priye, Lu Wei et al.· 0 citations
Immune therapies act across cell-intrinsic programs, tissue ecosystems, and patient-specific immune states, yet most predictors address these scales separately. We used a governed evolutionary AI Scientist to construct the Immune World Model, an action-conditioned model that learns how interventions move immune states...
Taoyong Cui, Xi Wang, Zonghang Li et al.· 0 citations
Deep neural networks are highly over-parameterized, and different parameter values represent the same predictive function. This makes their effective complexity difficult to measure using only the number of parameters or the rank of the Hessian. Singular Learning Theory addresses this issue through the local learning c...
Vishnu Varadarajan, Mihir More, Aritra Das et al.· 0 citations
On-policy distillation (OPD) has become a standard approach for transferring capabilities from large teachers to compact students. Its cost, however, is dominated by autoregressive student rollouts and scales poorly in multi-turn agentic settings. Existing acceleration methods truncate or relocate the supervision signa...
Zhiyu Gui, Kexin Huang, Jia Guo et al.· 0 citations
Martin Trust Center Managing Director Bill Aulet introduces Dear Dreamer, a free platform for middle and high school students who want to learn about entrepreneurship.
Microsoft Research Blog· microsoft.comSep 30, 2026
Extreme space-weather events can damage power systems on Earth and degrade GPS accuracy and satellite operations. A new machine learning system can predict where damage is likely to occur 30-60 minutes before a storm arrives. The post Forecasting space weather risks on power grids appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
MIT News · Artificial Intelligence· news.mit.eduSep 25, 2026
