Golden State Valkyries and New York Liberty headline two WNBA picks for tonight's slate LA Sparks star directs explicit rant at Enes Kanter Freedom over trans debate: 'Stupid piece of s---' Governor Landry backs Lane Kiffin, LSU in fight with SEC: 'Don't hate the player, hate the game' Giants QB's girlfriend takes NFL preseason fashion to next level, 9U football kid unloads & Horvat kids' clubs Vinod Khosla knows little about owning an NFL team but it's fine because he just bought the Super Bowl champs MLB stadium looks virtually empty as fans send clear message about the team: 'Embarrassing' Defense didn't give the jury a'path to not guilty': Donna Rotunno Jonathan Turley argues Lindsay Clancy's defense'lost ground' during closing arguments Historic cross fight could'unravel' LA community traditions, lawyer warns House Dems appoint pro-Israel lawmakers in blow to party's far-left wing Ritter: Clancy prosecution was'surprisingly' effective in closing arguments'Survivor' star Christian Hubicki talks China's wild Robot Olympics: 'They're willing to break the robots': Brit struggles to define'woman' in spectacular exchange Tennessee's Vol Navy started the tradition in 1962, and now stadiums across the country draw thousands of boats on game day Boaters and party-goers gathered in Boca Raton, Florida, for the annual Boca Bash. The event featured a flotilla of vessels, ranging from yachts to jet skis, under clear skies and a law enforcement presence. So in 1962, a Knoxville sportscaster named George Mooney actually did something about it -- he got in a ski boat, rode the Tennessee River to Neyland Stadium, tied off to a tree and walked into the game. Sixty-plus years later, sailgating is its own gameday subculture, with dedicated marinas, waitlists longer than season-ticket lines, and fans who'd rather anchor in a lake than fight for a parking spot. You don't need a stadium sitting directly on the water to pull this off -- plenty of these spots involve a walk from the dock -- but these are the ones where the boat crowd is as much a part of Saturday (or Sunday) as the game itself.

Existing evaluation protocols for brain visual decoding predominantly rely on coarse metrics that obscure inter-model differences, lack neuroscientific foundation, and fail to capture fine-grained visual distinctions. To address these limitations, we introduce BASIC, a unified, multigranular evaluation framework that jointly quantifies structural fidelity, inferential alignment, and contextual coherence between decoded and ground-truth images. For the structural level, we introduce a hierarchical suite of segmentation-based metrics, including foreground, semantic, instance, and component masks, anchored in granularity-aware correspondence across mask structures. For the semantic level, we extract structured scene representations encompassing objects, attributes, and relationships using multimodal large language models, enabling detailed, scalable, and context-rich comparisons with ground-truth stimuli. We benchmark a diverse set of visual decoding methods across multiple stimulus-neuroimaging datasets within this unified evaluation framework. Together, these criteria provide a more discriminative, interpretable, and comprehensive foundation for evaluating brain visual decoding methods.

Quantization (Alistarh et al., 2017) is an important (stochastic) compression technique that reduces the volume of transmitted bits during each communication round in distributed model training. Suresh et al. (2022) introduce correlated quantizers and show their advantages over independent counterparts by analyzing distributed SGD communication complexity. We analyze the forefront distributed non-convex optimization algorithm MARINA (Gorbunov et al., 2022) utilizing the proposed correlated quantizers and show that it outperforms the original MARINA and distributed SGD of Suresh et al. (2022) with regard to the communication complexity. We significantly refine the original analysis of MARINA without any additional assumptions using the weighted Hessian variance (Tyurin et al., 2022), and then we expand the theoretical framework of MARINA to accommodate a substantially broader range of potentially correlated and biased compressors, thus dilating the applicability of the method beyond the conventional independent unbiased compressor setup. Extensive experimental results corroborate our theoretical findings.

We study the MARINA method of Gorbunov et al (2021) -- the current state-of-the-art distributed non-convex optimization method in terms of theoretical communication complexity. Theoretical superiority of this method can be largely attributed to two sources: the use of a carefully engineered biased stochastic gradient estimator, which leads to a reduction in the number of communication rounds, and the reliance on {\em independent} stochastic communication compression operators, which leads to a reduction in the number of transmitted bits within each communication round. In this paper we i) extend the theory of MARINA to support a much wider class of potentially {\em correlated} compressors, extending the reach of the method beyond the classical independent compressors setting, ii) show that a new quantity, for which we coin the name {\em Hessian variance}, allows us to significantly refine the original analysis of MARINA without any additional assumptions, and iii) identify a special class of correlated compressors based on the idea of {\em random permutations}, for which we coin the term Perm$K$, the use of which leads to $O(\sqrt{n})$ (resp. $O(1 + d/\sqrt{n})$) improvement in the theoretical communication complexity of MARINA in the low Hessian variance regime when $d\geq n$ (resp. $d \leq n$), where $n$ is the number of workers and $d$ is the number of parameters describing the model we are learning. We corroborate our theoretical results with carefully engineered synthetic experiments with minimizing the average of nonconvex quadratics, and on autoencoder training with the MNIST dataset.

We're excited to announce our 4th WiMLDS Montreal meetup presented and hosted by BDC! Whether you're a data professional or simply curious, you are welcome regardless of your technical level or your gender. The talks will be entirely in English. Agenda 6:00 pm -- Doors open 6:30 pm -- Talks 7:45 pm -- Panel 8:30 pm -- Networking Opening remarks Amy Pollard -- Analyst @ Strategic Investments & BDC Women in Tech Fund Amy is involved in all aspects of the deal process including sourcing and due diligence. She is also responsible for portfolio management activities including portfolio monitoring, reporting and bi-annual portfolio valuations. Since founding her first entrepreneurial venture as a teenager, Amy has actively volunteered in global entrepreneurial and tech communities through organizations such as Startup Canada, Startup Weekend, Startup Nations and Junior Achievement.