We develop algorithms for private stochastic convex optimization that adapt to the hardness of the specific function we wish to optimize. While previous work provide worst-case bounds for arbitrary convex functions, it is often the case that the function at hand belongs to a smaller class that enjoys faster rates. Concretely, we show that for functions exhibiting κ-growth around the optimum, i.e., f ( x) f (x

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

One critical flaw of voting is its susceptibility to strategic manipulations. That is, agents may have an incentive to misreport their preferences (i.e.